Author: claimsbot

1. A method of generating a feature vector, the method comprising:
detecting a feature point from an input image based on a dominant direction of a gradient distribution in the input image; and
generating a feature vector corresponding to the feature point.
2. The method of claim 1, wherein the detecting of the feature point comprises:
detecting a pixel corresponding to a window having a contrast of coherence in a dominant direction.
3. The method of claim 1, wherein the generating of the feature vector comprises:
accumulating a strength of coherence in a dominant direction within a local area corresponding to the feature point to generate the feature vector.
4. The method of claim 1, wherein the detecting of the feature point comprises:
calculating a gradient for a plurality of pixels comprised in the input image;
calculating a structure tensor for the plurality of pixels based on the gradient;
calculating a maximum eigenvalue for the plurality of pixels by performing an Eigen analysis on the structure tensor; and
determining the feature point through a contrast amongst maximum eigenvalues.
5. The method of claim 4, wherein the calculating of the structure tensor for the plurality of pixels comprises:
when the input image is a video image, calculating a structure tensor of a single pixel based on a matrix
\u2211
B

\ue89e

G
x
2
\u2211
B

\ue89e
G
x

\ue89e

G
y
\u2211
B

\ue89e
G
x

\ue89e

G
t
\u2211
B

\ue89e
G
x

\ue89e

G
y
\u2211
B

\ue89e

G
y
2
\u2211
B

\ue89e
G
y

\ue89e

G
t
\u2211
B

\ue89e
G
x

\ue89e

G
t
\u2211
B

\ue89e
G
y

\ue89e

G
t
\u2211
B

\ue89e

G
t
2
,
wherein Gx denotes a gradient in an x axis direction, Gy denotes a gradient in a y axis direction, Gt denotes a gradient in a time axis direction, and B denotes a predetermined size of a block comprising the single pixel.
6. The method of claim 4, wherein the calculating of the structure tensor for the plurality of pixels comprises:
when the input image is a still image, calculating a structure tensor of a single pixel based on a matrix
\u2211
B

\ue89e

G
x
2
\u2211
B

\ue89e
G
x

\ue89e

G
y
\u2211
B

\ue89e
G
x

\ue89e

G
y
\u2211
B

\ue89e

G
y
2
,
wherein Gx denotes a gradient in an x axis direction, Gy denotes gradient in a y axis direction, and B denotes a predetermined size of a block comprising the single pixel.
7. The method of claim 4, wherein the determining of the feature point comprises:
calculating a sum of differences between a strength of coherence of a single pixel and strengths of coherence of neighboring pixels within a window corresponding to the single pixel; and
determining the single pixel to be the feature point when the sum is greater than a threshold value.
8. The method of claim 7, wherein the strength of coherence comprises at least one of:
a maximum eigenvalue of the single pixel; and
a difference between the maximum eigenvalue and another eigenvalue of the single pixel.
9. The method of claim 1, wherein the generating of the feature vector comprises:
with respect to a local pixels comprised in a local region,
mapping a dominant direction of a local pixel to predetermined bins; and
accumulating a dominant direction energy of the local pixel in the mapped bin.
10. The method of claim 9, wherein the dominant direction energy is a strength of coherence associated with a gradient of the local pixel, and the dominant direction corresponds to a maximum eigenvalue associated with the gradient of the local pixel.
11. The method of claim 9, wherein the predetermined bins quantize a time and a space of the input image to a predetermined number when the input image is a video image.
12. The method of claim 9, wherein the predetermined bins quantize the space of the input image to a predetermined number when the input image is a still image.
13. The method of claim 1, wherein the gradient comprises:
when the input image is a video image, a gradient in an x axis direction in a frame comprised in the input image, a gradient in a y axis direction in the frame comprised in the input image, and a gradient in a time axis direction between frames comprised in the input image.
14. The method of claim 1, wherein the gradient comprises:
when the input image is a still image, a gradient in an x axis direction in a frame comprised in the input image and a gradient in a y axis direction in the frame comprised in the input image.
15. The method of claim 1, further comprising generating of the feature vector corresponding to the input image based on a frequency characteristic extracted from the input image.
16. The method of claim 1, further comprising:
dividing the input image into combinations of a plurality of global regions using a spatial pyramid; and
extracting frequency characteristics of the plurality of global regions comprised in the combinations of the plurality of global regions, and generating feature vectors corresponding to the plurality of global regions.
17. A method of image processing, the method comprising:
detecting a plurality of feature points comprised in an input image based on a dominant direction of a gradient distribution in the input image;
generating a plurality of feature vectors corresponding to the plurality of feature points; and
mapping the plurality of feature vectors to codewords in a codebook, to generate a histogram corresponding to the input image based on the mapped feature vectors.
18. The method of claim 17, further comprising:
analyzing the input image based on a learned parameter and the histogram.
19. The method of claim 18, wherein the learned parameter is generated by pre-learning a plurality of training images based on the dominant direction analysis of the gradient distribution.
20. The method of claim 18, wherein the analyzing of the input image comprises:
recognizing content of the input image.
21. The method of claim 20, wherein the content of the input image comprises at least one of:
a behavior of a performer comprised in the input image; and
an object comprised in the input image.
22. The method of claim 17, wherein the generating of the histogram comprises:
normalizing values corresponding to the codewords, and generating a normalized histogram.
23. The method of claim 17, further comprising:
detecting a set of feature points from a plurality of training images based on the dominant direction analysis;
generating feature vectors corresponding to a portion of feature points selected arbitrarily from among the set of feature points; and
clustering the feature vectors corresponding to the portion of feature points, and generating the codebook.
24. The method of claim 17, wherein the detecting of the plurality of feature points comprises:
detecting pixels corresponding to windows having a contrast of coherence in a dominant direction to be the plurality of feature points.
25. The method of claim 17, wherein the generating of the plurality of feature vectors comprises:
accumulating a strength of coherence in the dominant direction within a local region corresponding to the plurality of feature points in order to generate the plurality of feature vectors.
26. The method of claim 17, further comprising:
generating a global feature vector corresponding to the input image based on a frequency characteristic extracted from the input image; and
combining the histogram and the global feature vector.
27. The method of claim 17, further comprising:
unsupervised learning of the histogram, and generating a mid-level feature vector.
28. A non-transitory computer-readable medium comprising a program for instructing a computer to perform the method of claim 1.
29. An apparatus for learning a classifier, the apparatus comprising:
a detector to detect a plurality of feature points comprised in a plurality of training images based on a dominant direction analysis of a gradient distribution;
a generator to generate a plurality of feature vectors corresponding to the plurality of feature points;
a mapper to map the plurality of feature vectors to codewords comprised in a given codebook, and generate a histogram corresponding to the plurality of training images; and
a learning unit to learn a classifier based on the histogram.
30. The apparatus of claim 29, wherein the learning unit inputs the histogram and a label of the plurality of training images into the classifier in order to learn the classifier.
31. The apparatus of claim 29, further comprising:
a clustering unit to cluster the plurality of feature vectors, and generating the codebook.
32. The apparatus of claim 29, wherein the detector detects pixels corresponding to windows having a contrast of coherence in a dominant direction to be the plurality of feature points.
33. The apparatus of claim 29, wherein the generator accumulates a strength of coherence in a dominant direction of a local region corresponding to the plurality of feature points in order to generate the plurality of feature vectors.
34. The apparatus of claim 29, wherein the mapper maps the plurality of feature vectors generated from a corresponding training image from among the plurality of training images, and generates a histogram corresponding to the corresponding training image.
35. The apparatus of claim 29, wherein the mapper normalizes values corresponding to the codewords, and generates a normalized histogram.
36. A recognition apparatus, the apparatus comprising:
a detector to detect a plurality of feature points comprised in an input image based on a dominant direction analysis of a gradient distribution;
a generator to generate a plurality of feature vectors corresponding to the plurality of feature points;
a mapper to map the plurality of feature vectors comprised in a given codebook, and generate a histogram corresponding to the input image; and
a recognizer to recognize content of the input image based on a learned parameter and the histogram.
37. The apparatus of claim 36, wherein the content of the input image comprises at least one of a behavior of a performer comprised in the input image; and
an object comprised in the input image.
38. The apparatus of claim 36, wherein the learned parameter is generated by pre-learning a plurality of training images based on the dominant direction analysis of the gradient distribution.
39. The apparatus of claim 36, wherein the detector detects pixels corresponding to windows having a contrast of coherence in a dominant direction to be the plurality of feature points.
40. The apparatus of claim 36, wherein the generator accumulates a strength of coherence in a dominant direction of a local region corresponding to the plurality of feature points in order to generate the plurality of feature vectors.
41. A detection apparatus, the apparatus comprising:
a feature point detector to detect a plurality of feature points comprised in at least a portion of an input image based on a dominant direction analysis of a gradient distribution;
a generator to generate a plurality of feature vectors corresponding to the plurality of feature points;
a mapper to map the plurality of feature vectors to codewords comprised in a given codebook, and generate a histogram corresponding to the at least one portion; and
a region detector to compare a reference histogram to the histogram, and detect a region corresponding to the reference histogram.
42. The apparatus of claim 41, wherein the feature point detector detects a plurality of reference feature points comprised in a reference image based on the dominant direction analysis of the gradient distribution,
the generator generates a plurality of reference feature vectors corresponding to the plurality of reference feature points, and
the mapper maps the plurality of reference feature vectors to the codewords, and generates the reference histogram corresponding to the reference image.

The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.

1. A method for automated fare collection in a transit system, the method comprising:
using an RFID-enabled card reader coupled to a terminal controller to read a contactless payment card presented by a customer to gain access to gated pay areas of the transit system;
evaluating the read contactless payment card against a file having list of cards and accordingly granting or denying the customer access to gated pay areas of the transit system;
preparing and communicating a card transaction record to a transit payment platform; and
then at the transit payment platform, processing the card transaction record so that the transit system can automatically collect a fare for the customer granted access to the transit system pay area.
2. The method of claim 1 further comprising communicating the file with the list of cards from the transit payment platform to terminal controller coupled to RFID-enabled card reader, wherein the list of cards comprises cards that are lost, stolen and delinquent.
3. The method of claim 1, wherein processing the card transaction record at the transit payment platform comprises authorization, clearing and settlement of a card transaction over a commercial payment-by-card electronic network linked to an issuer of the contactless payment card presented by a customer.
4. The method of claim 3 further comprising conforming to open ISO industry standards for contactless payment cards and transaction payment processing.
5. The method of claim 3 wherein authorization, clearing and settlement of the card transaction over a commercial payment-by-card electronic network linked to an issuer of the contactless payment card presented by a customer further comprises authorization of aggregated card transactions.
6. The method of claim 1, wherein processing the card transaction record at the transit payment platform so that the transit system can automatically collect a fare for the customer granted access to the transit system pay area comprises determining whether the contactless payment card presented by the customer is an unregistered card or previously registered card associated with a pre-funded transit payment account.
7. The method of claim 6, further comprising:
for an unregistered card, setting up a fare aggregation account; and
for previously registered card, setting a fare as per a pre-registration fare schedule
8. The method of claim 6, wherein setting up a fare aggregation account for an unregistered card comprises:
obtaining authorization or approval for setting up a fare aggregation account for the card; and
if the card is approved, setting up a fare aggregation account with rules on when an aggregated transaction must be posted for clearing and settlement;

wherein the rules include at least one of a rule on an aggregation amount limit, a rule on an aggregation time limit; a rule on aggregation account status when the card is lost, stolen and delinquent, and a rule on aggregation account status if the card is later registered.
9. The method of claim 6, wherein for a registered card associated with a pre-funded transit payment account processing the card transaction record at the transit payment platform so that the transit system can automatically collect a fare for the customer granted access to the transit system pay area comprises checking the balance of the pre-funded transit payment account and obtaining a fare payment from the pre-funded transit payment account.
10. The method of claim 9, wherein when the balance of the pre-funded transit payment account is insufficient to obtain the fare payment from the pre-funded transit payment account the method further comprises adding the card to a list of cards that are lost, stolen and delinquent.
11. The method of claim 6, wherein the pre-funded transit payment account is a ride entitlement account and checking the balance of the pre-funded transit payment account comprises checking availability of a ride entitlement and obtaining a fare payment from the pre-funded transit payment account comprises deducting a ride entitlement from the account.
12. The method of claim 1, wherein processing the card transaction record then at the transit payment platform so that the transit system can automatically collect a fare for the customer granted access to the transit system pay area comprises implementing a transit system fare schedule.
13. The method of claim 1, wherein processing the card transaction record so that the transit system can automatically collect a fare for the customer granted access to the transit system comprises calculating the fare after the cardholder is granted access.
14. A system for automated fare collection in a transit system for collecting fares from a customer presenting an RFID-enabled smart card issued by a commercial card issuer to access a transit system pay area, the system comprising:
a transit payment platform;
an RFID-enabled card reader disposed at gate leading to the transit system pay area, the card reader configured to contactlessly read the smart card presented by the customer;
a terminal controller interfaced with the card reader, the terminal controller and the card reader configured to accept or reject the smart card read by the card reader against a file having list of cards and to accordingly grant or deny access to the customer through the gate, and further configured to generate and communicate a card transaction record to the transit payment platform;

wherein the transit payment platform is configured to process the card transaction record so that the transit system can automatically collect a fare the customer granted access to the transit system pay area.
15. The system of claim 14, wherein the transit payment platform comprises an authorizationclearing application linked to a payment-by-card electronic network for authorization, clearing and settlement of payment card transactions.
16. The system of claim 15, wherein the smart card and the payment-by-card electronic network conform to open ISO industry standards for contactless payments.
17. The system of claim 14, wherein the transit payment platform has a file application designed maintain the list of cards that includes cards that are lost, stolen or delinquent.
18. The system of claim 14, wherein the transit payment platform comprises a file application designed to maintain the list of cards and associated fare and ride entitlements.
19. The system of claim 14, wherein the transit payment platform comprises a customer account management application, which can link the smart card to a pre-funded transit account.
20. The system of claim 19, wherein the transit payment platform comprises a customer payment application designed to process the card transaction as one of a pre-funded account transaction account and a post-funded account transaction.
21. The system of claim 14, wherein the transit payment platform comprises a network management application designed to provide configuration updates to the RFID-enabled card reader and the terminal controller.
22. The system of claim 14, wherein the transit payment platform comprises an account maintenance application designed to implement a transaction fare according to a transit system fare schedule.
23. The system of claim 14, wherein the transit payment platform comprises a transit customer interface designed to provide the customer interactive access to account features and transaction reports.

1. A fuse comprising:
a fuse element having a pair of flat plate portions forming terminal portions at both ends of the fuse element and a fusible portion provided between opposed inner edges of the pair of flat plate portions, the flat plate portions being formed to have a uniform thickness; and
an insulating housing formed in a box shape and provided to cover inner edge sides of the pair of flat plate portions and the fusible portion in a state in which outer edge sides of the pair of flat plate portions are protruded outward from slits formed at opposed end walls of the insulating housing,
wherein the pair of flat plate portions protruded outward from the slits at the end walls of the insulating housing are folded into a plurality of layers to form the outer edge sides of the flat plates as the terminal portions each having a greater thickness than each of the flat plate portions, and
wherein protrusions provided on side edges of portions of the pair of flat plate portions placed inside the insulating housing abut against inner surfaces of the end walls of the insulating housing.
2. The fuse according to claim 1, wherein a fuse element insertion port from which the fuse element is inserted is provided at one end of the insulating housing, and
wherein one of the end walls is provided as a lid that closes the fuse element insertion port after inserting the fuse element, and in a state in which the fuse element insertion port is closed after inserting the fuse element, the lid is locked from an outside by one of the terminal portions formed by folding the flat plate portions.
3. A method for producing a fuse, the method comprising steps of:
preparing a fuse element having a pair of first and second flat plate portions forming terminal portions at both ends of the fuse element and a fusible portion provided between opposed inner edges of the first and second flat plate portions, at least the flat plate portions being formed by punching a flat metal plate having a uniform thickness;
preparing an insulating housing having a rectangular cylindrical body and a pair of end walls configured to close openings at end portions of the rectangular cylindrical body, one of the pair of end walls being provided as a fixed wall having a slit through which the first flat plate portion is inserted and fixedly closing one of the openings at the end portions of the rectangular cylindrical body, the other of the pair of end walls being rotatably connected to the rectangular cylindrical body via a hinge and provided as a lid that closes the other of the openings at the end portions of the rectangular cylindrical body after inserting the fuse element, the other of the openings being opened as a fuse element insertion port, and the lid having a slit through which the second flat plate portion is inserted on a side edge opposite to the hinge;
inserting the first flat plate portion of the fuse element into the insulating housing from the fuse element insertion port such that an outer edge side of the first flat plate portion protrudes outward from the insulating housing through the slit of the fixed wall and such that a protrusion provided on a side edge of the first flat plate portion abuts against an inner surface of the fixed wall to position the fuse element relative to the insulating housing, so that inner edge sides of the first and second flat plate portions and the fusible portion of the fuse element are accommodated inside the insulating housing;
rotating the lid after the inserting step to close the fuse element insertion port such that an outer edge side of the second flat plate portion is protruded outward from the insulating housing through the slit of the lid an such that the lid abuts against a protrusion provided on a side edge of the second flat plate portion to position the lid at a closed position;
folding the second flat plate portion protruded outward from the insulating housing into a plurality of layers after the lid has been closed, such that the outer edge side of the second flat plate portion is formed as a second terminal portion having a greater thickness than the flat metal plate and such that the lid is locked from an outside by the second terminal portion; and
folding the first flat plate portion into a plurality of layers after or before the fuse element is inserted into the insulating housing, such that the outer edge side of the flat plate portion is formed as a first terminal portion having a greater thickness than the flat metal plate.

The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.

1. An ultraviolet wastewater or water treatment system for disinfecting the wastewater or water by ultraviolet radiation, the system comprising:
a. a series of lamp modules forming a bank, each lamp module containing a plurality of ultraviolet lamps each having a longitudinal axis, each lamp having a protective cladding, made of a material transparent to ultraviolet light, disposed thereon;
b. a common drive assembly including:
i. a common drive;
ii. first and second actuators extending generally parallel to the longitudinal axes of the lamps;
iii. first and second mobile devices operatively connected to the first and second actuators respectively and to the common drive, and wherein the first and second mobile devices are movable back and forth along the first and second actuators respectively in a direction generally parallel to the longitudinal axes of the lamps;
iv. a transverse rod extending between the first and second mobile devices and extending generally perpendicular to the first and second actuators, wherein the transverse rod is operatively connected to the first and second mobile devices and is movable in a direction generally parallel to the longitudinal axes of the lamps;

c. a series of elongated beams for supporting the lamp modules, each beam being disposed over one of the modules and extending generally parallel to the longitudinal axes of the lamps and extending generally perpendicular to the transverse rod;
d. a plurality of carriages, each carriage being movably mounted on one of the beams and configured to be operatively connected to the transverse rod such that as the transverse rod moves, each carriage connected to the rod moves back and forth along one of the beams;
e. a plurality of scrapers, each scraper carried by and extending downwardly from one of the carriages for engaging and cleaning the protective cladding of the plurality of lamps in one of the modules as the carriages move back and forth along the beams; and
f. wherein the common drive is operable to move the first and second mobile devices back and forth along the first and second actuators, and wherein as the first and second mobile devices move relative to the actuators, the transverse rod and at least one of the carriages and its respective scraper moves in the same direction as the mobile devices.
2. The ultraviolet wastewater or water treatment system of claim 1 wherein the common drive is supported independently of the ultraviolet lamp modules.
3. The ultraviolet wastewater or water treatment system of claim 1 including an automatic attachment system for automatically attaching and detaching the common drive to at least one of the carriages.
4. The ultraviolet wastewater or water treatment system of claim 3 wherein the automatic attachment system includes at least two springs associated with each carriage.
5. The ultraviolet wastewater or water treatment system of claim 4 wherein the springs extend upwardly from each carriage in converging directions.
6. The ultraviolet wastewater or water treatment system of claim 5 wherein the transverse rod extends between the springs.
7. The ultraviolet wastewater or water treatment system of claim 3 wherein the automatic attachment system is configured to detach the common drive from the at least one of the carriages if the carriage or its respective scraper encounters a predetermined resistance to movement as the carriage moves along its respective beam.
8. The ultraviolet wastewater or water treatment system of claim 1 wherein the first and second actuators are disposed on opposite sides of the bank of lamps.