1. Method of seeking images, from an example image, from amongst a plurality of images stored in a database, each of said stored images being associated with a data item of a first type representing at least one characteristic of the visual content of the image, said method comprising the following steps:
each time a new image is stored in said database, associating with said new image a data item of a second type representing the location of at least one region of interest in said new image;
receiving a data item of the second type representing the location of at least one region of interest in said example image;
obtaining a data item of said first type associated with said example image;
calculating a similarity between the example image and each of the images amongst at least one subset of said stored images, the similarity being calculated from the data of the first type and of the second type associated respectively with said example image and with the stored image; and
supplying at least one image, referred to as the result image, of the database, said at least one result image being selected from amongst said stored images in the database according to its degree of similarity with the example image.
2. Image search method according to claim 1, wherein said data item of the first type is obtained for each of the stored images and for the example image by performing a first operation of dividing the image into a predefined number N of blocks followed by a second extraction operation for each of the blocks (Bi) of a data item representing the visual content of the block, said data item of the first type consisting of a vector (G(Im)) having N components each of which being the data item representing the visual content extracted for a block of the image.
3. Image search method according to claim 2, wherein the step of calculating a similarity, denoted SIM, between the example image Q and each of the images D from amongst at least one subset of stored images is performed by calculating a distance between the vector G(Q) associated with the example image and the vector G(D) associated with the stored image under consideration, said distance being weighted by means of a plurality N of weighting coefficients Wi, the value of each of which being indicative of a degree of proximity in one of the blocks Bi resulting from the division of the images, of regions of interest associated with the example image and with the stored image under consideration.
4. Image search method according to claim 3, wherein the step of calculating a similarity SIM is effected by calculating the sum of values, each of which, denoted dist(qi, di), being a measure of similarity between a component qi of the vector G(Q) corresponding to a given block Bi of said example image and the component di of the vector G(D) corresponding to the same block of the stored image under consideration, said similarity measurements dist(qi, di) being weighted by said weighting coefficients Wi whose value is indicative of a degree of proximity, in the said block, of regions of interest associated with the said example image and with the stored image under consideration.
5. Image search method according to claim 4, wherein said similarity SIM is obtained by means of the following formula:
6
SIM
=
i
=
1
N
W
i
dist
(
q
i
,
d
i
)
i
=
1
N
W
i
6. Image search method according to any one of claims 3 to 5, wherein said weighting coefficients Wi have a value which is a function of the surface area of the intersection between the regions of interest associated with the example image, those associated with the stored image under consideration, and the block under consideration of said example image and of the stored image under consideration.
7. Image search method according to claim 6, in which said example image Q contains any integer number R of regions of interest, denoted ROIr(Q), r being an integer between 1 and R, and the stored image under consideration D contains any integer number T of regions of interest, denoted ROIt(D), t being an integer between 1 and T, characterised in that each of said weighting coefficients Wi is obtained in accordance with the following formula:
7
W
i
=
i
=
1
T
r
=
1
R
P
i
r
,
i
with
P
i
r
,
i
=
area
(
B
i
ROI
r
(
Q
)
ROI
i
(
D
)
)
area
(
B
i
)
the index i being an integer number lying between 1 and said predefined number N of blocks.
8. Image search method according to any one of claims 2 to 7, wherein said data item representing the visual content of a block of the image represents the distribution of the colours (Hi) in said block.
9. Image search method according to claim 8, when it is combined with any one of claims 4 to 7, wherein each of said measurements of similarity dist(qi, di) between a component qi of the vector G(Q), corresponding to a given block Bi of said example image and the component di of the vector G(D) corresponding to the same block of the stored image under consideration, is obtained by calculating the intersection between these two components.
10. Image search method according to any one of the preceding claims, wherein said data item of the second type representing the location of at least one region of interest in each of the stored images and in the example image consists of a set of two-dimensional points indicative of the shape of said at least one region of interest and its location in the image plane of the image.
11. Image search method according to any one of claims 2 to 10, wherein said predefined number N of blocks is equal to sixteen.
12. Device for seeking images, from an example image, from amongst a plurality of images stored in a database, said device comprising means adapted to implement an image search method according to any one of the preceding claims.
13. Computer, comprising means adapted to implement an image search method according to any one of claims 1 to 11.
14. Computer, comprising an image search device according to claim 12.
15. Method of indexing digital images, comprising the following steps, for each image Im to be indexed:
dividing the image plane of the image Im, in accordance with a partitioning comprising a predefined number N of blocks Bi;
extracting from each of the blocks a data item of a first type representing at least one characteristic of the visual content of the block;
defining in the image at least one region of interest, and obtaining a data item of a second type representing the location of at least one region of interest in the image;
calculating for each of said blocks Bi a first coefficient, WiIm, indicating a degree of presence in the block Bi under consideration of said image of said at least one region of interest;
associating with said image Im an index composed of a first vector G(Im), having N components, each of which being one of the data items of the first type, and a second vector W(Im), having N components, each of which being one of said first coefficients WiIm.
16. Image indexing method according to claim 15, in which said image Im contains any integer number R of regions of interest, denoted ROIr, r being an integer between 1 and R, and wherein the step of calculating a first coefficient for each of said blocks Bi, said first coefficient WiIm is obtained by means of the following formula:
8
W
i
l
m
=
W
o
+
r
=
1
R
P
i
r
in which W0 is a predefined constant, and Pir is a coefficient indicating a degree of presence of the corresponding region of interest ROIr, in the block Bi under consideration of the image plane of the image Im.
17. Image indexing method according to claim 16, wherein each coefficient Pir is obtained by calculating the ratio between the surface area of the intersection between the block Bi under consideration and the corresponding region of interest ROIr, and the surface area of the block Bi under consideration.
18. Image indexing method according to any one of claims 15 to 17, wherein said data item of the second type representing the location of said at least one region of interest in the said image consists of a set of two-dimensional points indicative of the shape of said at least one region of interest and its location in the image plane of said image.
19. Image indexing method according to any one of claims 15 to 18, wherein said data item of the first type representing at least one characteristic of the visual content of a block of said image represents the distribution of the colours in said block.
20. Image indexing method according to any one of claims 15 to 19, wherein the image plane of said image Im is divided in accordance with a rectangular grid.
21. Image indexing method according to claim 20, wherein said predefined number N of blocks is equal to sixteen.
22. Method of seeking images, from an example image, amongst a plurality of images stored in a database, wherein said example image and each of said stored images are indexed according to an image indexing method according to any one of claims 15 to 21.
23. Image search method according to claim 22, comprising the following steps of:
calculating a similarity SIM between the example image Q and each of the images D from amongst at least one subset of the stored images, the similarity being calculated from first vectors G(Q), G(D), and second vectors W(Q), W(D), associated respectively with the example image Q and the stored image D; and
supplying at least one images referred to as the result image, in the database, said at least one result image being selected from amongst the stored images in the database according to its degree of similarity with the example image.
24. Image search method according to claim 23, wherein the step of calculating a similarity SIM between said example image Q and each of the images D from amongst at least one subset of said stored images is implemented by calculating a distance between the first vector G(Q) associated with said example image and the first vector G(D) associated with the stored image under consideration, said distance being weighted by means of a plurality N of weighting coefficients Ri, whose value is calculated as a function of the components WiQ, WiD of the second vectors W(Q) and W(D) associated respectively with the example image Q and the stored image D under consideration.
25. Image search method according to claim 24, wherein the value of the weighting coefficients Ri is obtained in accordance with the following formulae:
RiWiQWiD
if WiQ and WiD are both strictly greater than said predefined constant W0 and
RiWiQWiDW0
in the other cases.
26. Image search method according to claim 24 or 25, wherein said similarity value SIM is obtained by calculating the sum of values, each of which, denoted dist(qi, di), being a measurement of similarity between a component qi of the first vector G(Q) corresponding to a given block Bi of the example image Q and the component di of the first vector G(D) corresponding to the same block of the stored image D under consideration, these similarity measurements dist(qi, di) being weighted by the weighting coefficients Ri.
27. Image search method according to claim 26, wherein said similarity SIM is obtained by means of the following formula:
9
SIM
=
i
=
1
N
R
i
dist
(
q
i
,
d
i
)
i
=
1
N
R
i
28. Image search method according to claim 27, when it is combined with claim 19, 20 or 21, wherein each of said measurements of similarity, dist(qi, di), between a component qi of the vector G(Q) corresponding to a given block Bi of the example image Q and the component di of the vector G(D) corresponding to the same block in the stored image under consideration D, is obtained by calculating the intersection between these two components.
29. Device for seeking images, from an example image, amongst a plurality of images stored in a database, said device comprising means adapted to implement an image indexing method according to any one of claims 15 to 21, andor an image search method according to any one of claims 22 to 28.
30. Computer, comprising means adapted to implement an image indexing method according to any one of claims 15 to 21, andor an image search method according to any one of claims 22 to 28.
31. Computer, comprising an image search device according to claim 29.
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 computer-readable memory having contents adapted to cause a computer, coupled to a mobile integrated communications appliance in which a plurality of off-the-shelf communication components are operably interconnected, to perform a method for simplifying user deployment and maintenance of the appliance, the method comprising:
configuring off-the-shelf communication components connected in the mobile integrated communications appliance for establishing a self-supported communications network;
monitoring the status of components of the mobile integrated communications appliance including operably interconnected off-the-shelf communication components;
performing maintenance of off-the-shelf communication components operably interconnected in the mobile integrated communications appliance;
conveying, on an output device, system status information indicating the monitored status of components of the mobile integrated communications appliance including operably interconnected off-the-shelf communication components; and
presenting, on a user interface display, one or more configuration and maintenance wizards, wherein each wizard:
presents a sequence of step-by-step instructions to the user for configuring or maintaining one or more of the components of the mobile integrated communications appliance including off-the-shelf communication components;
receives, from an input device, user input in response to the presented sequence of step-by-step instructions; and
configures or maintains the one or more components based on the received user input.
2. The computer-readable memory of claim 1 wherein the configuring comprises interfacing with the operably interconnected off-the-shelf communication components and setting parameters for the components such that the components work together in the appliance.
3. The computer-readable memory of claim 2 wherein the parameters for a component comprise one or more of firmware updates, time synchronization settings, log handling, bandwidth allocation, access policies, and user data.
4. The computer-readable memory of claim 1 wherein the configuring comprises automatic configuration of off-the-shelf communication components operably interconnected in the mobile integrated communications appliance to communicate with one or more connected telecommunication systems.
5. The computer-readable memory of claim 4 wherein the automatic configuration comprises one or more of off-the-shelf communication component and accessory discovery, telephone dialing protocol determination, telephone trunking configuration setup, wireless channel settings, and bandwidth allocation on backhaul links.
6. The computer-readable memory of claim 1 wherein the configuring comprises setup of one or more of a land mobile radio (LMR) transmitter, a radio over IP (RoIP) device, a satellite radio, a software-defined radio, and a cross-radio gateway.
7. The computer-readable memory of claim 1 wherein the configuring comprises compliance with communication protocols for classified networks.
8. The computer-readable memory of claim 1 wherein the configuring comprises controlling the power-up sequence of off-the-shelf communication components operably interconnected in the mobile integrated communications appliance.
9. The computer-readable memory of claim 1, further comprising presenting on a user interface display an operations menu configured to allow the user to launch the configuration and maintenance wizards.
10. The computer-readable memory of claim 1 wherein the monitored appliance components include the monitoring software.
11. The computer-readable memory of claim 1 wherein the monitored appliance components include telephone connections.
12. The computer-readable memory of claim 1 wherein the monitored appliance components include a cooling system, comprising one or more of a fan, a duct, a filter, and a sensor measuring one or more temperatures of the appliance and its components.
13. The computer-readable memory of claim 1 wherein the monitored appliance components include one or more devices positionable remote from the mobile integrated communications appliance and operably coupled to components in the mobile integrated communications appliance.
14. The computer-readable memory of claim 13 wherein a remote device operably coupled to the first mobile integrated communications appliance is an off-the-shelf communication component operably interconnected in a second mobile integrated communications appliance.
15. The computer-readable memory of claim 1 wherein a malfunction in a monitored component causes an alert to appear on the user interface display.
16. The computer-readable memory of claim 1 wherein the system status information conveyed on the output device includes a plurality of status indicators, each representing the operational health of a component.
17. The computer-readable memory of claim 16 wherein the status indicators are displayed on a graphical user interface screen.
18. The computer-readable memory of claim 17 wherein, for an indicator that represents an unhealthy status, the user interface provides a user-selectable link to additional detail about the problem or an action to fix the problem.
19. The computer-readable memory of claim 1, further comprising:
presenting a user-selectable option to save at least a portion of the state of the mobile integrated communications appliance to a storage device; and
presenting a user-selectable option to load the previously saved state of a mobile integrated communications appliance from the storage device.
20. The computer-readable memory of claim 19 wherein portions of the state of the configured mobile integrated communications appliance that can be saved and loaded include:
component configuration;
network configuration; and
user configuration.
21. The computer-readable memory of claim 19 wherein the storage device is external to the mobile integrated communications appliance.
22. The computer-readable memory of claim 1, further comprising managing remotely deployed network extension devices.
23. The computer-readable memory of claim 22 wherein the managing comprises creation of a one-to-one, a one-to-many, or a many-to-many network.
24. The computer-readable memory of claim 22 wherein the managing comprises increasing the range of a communications network provided by off-the-shelf communication components operably interconnected in the mobile integrated communications appliance.
25. The computer-readable memory of claim 1 wherein the monitoring, configuring, and performing maintenance comprise real-time system performance monitoring and iterative adjustment of monitored components to optimize communication quality.
26. The computer-readable memory of claim 25 wherein real-time system performance monitoring and iterative adjustment of monitored components is managed by state-driven components that use multiple Bayesian models to analyze system behavior and identify errors or opportunities for real-time optimization.
27. The computer-readable memory of claim 1 wherein the performing maintenance comprises automatic remediation of errors based on a knowledge base of diagnostic and remediation procedures.