1. A system for determining an estimated age of an individual, the system comprising:
a memory for storing computer executable instructions; and
a processing unit for accessing the memory and executing the computer executable instructions, the computer executable instructions comprising:
an age class estimator to classify a plurality of images of the individual into age classes, each age class corresponding to an interval of age, and each image having a known time stamp;
a probability determination engine to determine, for each age class, a value of class probability that an image in the collection falls within the age class; and
an age determination engine to determine a transition time based on the values of class probability and the known time stamp, and to determine the estimated age of the individual based on the determined transition time.
2. The system of claim 1, wherein the probability determination engine comprises instructions executable to compute the value of class probability that the image falls within the age class based on a value of probability that a subset of images in the collection falls within the age class, and wherein the subset of images have time stamps that falls within an interval of time that encompasses the known time stamp of the image.
3. The system of claim 1, wherein the age class estimator comprises instructions executable to perform face detection on an image collection, identify images in the image collection that comprise the individual based on the face detection, and classify the identified images into age classes based on the face detection.
4. The system of claim 1, wherein, to determine the transition time, the age determination engine comprises computer executable instructions to:
for each age class, fit an age class function to the computed probabilities for images classified in the age class based on the time stamp of the images, wherein each age class function corresponds to a respective age class; and
determine the transition time as a value of a cross-point between age class function fits that is above a predetermined threshold value.
5. The system of claim 4, wherein each age class function is a time-dependent polynomial function.
6. The system of claim 5, wherein the time-dependent polynomial function (Pi\u2032) is computed according to Pi\u2032(t)=ai1t2+ai2t+ai3, wherein i corresponds to each age class, wherein t is time, wherein ai1, ai2, and ai3 are coefficients derived from the fit, wherein the transition time (T) is at the cross-point between the fits to two different age class functions Pi\u2032 and Pj\u2032, and wherein Pi\u2032(T)=Pj\u2032(T).
7. The system of claim 4, wherein multiple cross-points between age class function fits are above the predetermined threshold value, the age determination engine comprises further comprising instructions executable to:
determine a transition time that corresponds to each cross-point; and
determine the estimated age of the individual based on the multiple transition times.
8. The system of claim 4, wherein the pre-determined threshold is a value of probability of about 0.35.
9. The system of claim 1, wherein, to determine the age of the individual based on the transition time, the age determination engine further comprises instructions executable to compute a difference between the transition time and a predetermined standardized value corresponding to the cross-point between the two age class function fits, and determine the estimated age of the individual based on the difference.
10. A method performed by a physical computing system comprising at least one processor for determining an age of an individual, said method comprising:
using an age class estimator, classifying a plurality of images of the individual into age classes, each age class corresponding to an interval of age, and each image having a known time stamp;
determining, for each age class, a value of class probability that an image in the plurality of images falls within the age class;
determining a transition time based on the values of class probability and the known time stamp; and
determining the estimated age of the individual based on the determined transition time.
11. The method of claim 10, further comprising determining the value of class probability that the image falls within the age class based on a value of probability that a subset of images in the collection falls within the age class, and wherein the subset of images have time stamps that falls within an interval of time that encompasses the known time stamp of the image.
12. The method of claim 10, wherein determining the transition time comprises:
for each age class, fitting an age class function to the computed probabilities for images classified in the age class based on the time stamp of the images, wherein each age class function corresponds to the respective age class; and
determining the transition time as a value of a cross-point between age class function fits that are above a predetermined threshold value.
13. The method of claim 12, wherein each age class function is a time-dependent polynomial function.
14. The method of claim 13, wherein the polynomial function is computed according to Pi\u2032=ai1t2+ai2t+ai3, wherein i corresponds to an age class, wherein t is time, wherein ai1, ai2, and ai3 are constants derived from the fitting, wherein the transition time (T) is at the cross-point between the fits to two different age class function Pi\u2032 and Pj\u2032, and wherein Pi\u2032(T)=Pj\u2032(T).
15. The method of claim 12, wherein multiple cross-points between age class function fits are above the predetermined threshold value, and wherein determining the estimated age of the individual further comprises:
determining a transition time that corresponds to each cross-point; and
determining the estimated age of the individual based on the multiple transition times.
16. The method of claim 12, wherein the pre-determined threshold is a value of probability of 0.35.
17. The method of claim 10, wherein computing the age of the individual based on the transition time comprises determining the difference of the transition time and a predetermined standardized value corresponding to the cross-point between the two age class functions, and determining the estimated age of the individual based on the difference.
18. A non-transitory computer readable medium having computer executable instructions comprising:
an age class estimator to classify a plurality of face images of the individual into age classes, each age class corresponding to an interval of age, and each face image having a known time stamp;
a probability determination engine to determine, for each age class, a value of class probability that an image in the collection falls within the age class; and an age determination engine to determine a transition time based on the values of class probability and the known time stamp, and to determine the estimated age of the individual based on the determined transition time.
19. A non-transitory computer readable medium of claim 18, wherein the probability determination engine comprises instructions executable to compute the value of class probability that the image falls within the age class based on a value of probability that a subset of images in the collection falls within the age class, and wherein the subset of images have time stamps that falls within an interval of time that encompasses the known time stamp of the image.
20. A non-transitory computer readable medium of dam 18, wherein, to determine the transition time, the age determination engine comprises computer executable instructions to: for each age class, fit an age class function to the computed probabilities for images classified in the age class based on the time stamp of the images, wherein each age class function corresponds to the respective age class; and determine the transition time as a value of a cross-point between age class function fits that are above a predetermined threshold value.
21. The non-transitory computer readable medium of claim 20, wherein each age class function is a time-dependent polynomial function (Pi\u2032) computed as Pi\u2032=ai1t2+ai2t+ai3, wherein i corresponds to each age class, wherein t is time, and wherein ai1, ai2, and ai3 are constants derived from the fit, wherein the transition time (T)is at the cross-point between the fits to two different age class function age class functions Pi\u2032 and Pj\u2032, and wherein Pi\u2032(T)=Pj\u2032(T).
22. The non-transitory computer readable medium of claim 20, wherein multiple cross-points between age class function fits are above the predetermined threshold value, the age determination engine comprises further comprising instructions executable to: determine a transition time that corresponds to each cross-point; and determine the estimated age of the individual based on the multiple transition times.
23. A non-transitory computer readable medium of claim 18, wherein, to determine the age of the individual based on the transition time, the age determination engine further comprises instructions executable to compute a difference of the transition time and a predetermined standardized value corresponding to the cross-point between the two age class functions, and determine the estimated age of the individual based on the difference.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
I claim:
1) An apparatus to facilitate connection of a dryer having a vent pipe extending from a rear side portion thereof, to an exhaust pipe extending outwardly from a wall, comprising:
a pan portion having a bottom side portion having a peripheral edge portion and a lateral sidewall connected around and extending away from the peripheral edge portion and an inner side of the bottom portion;
said lateral sidewall adapted to laterally and resiliently compress; and,
a short tubular section having one end portion adapted to fit closely together with the dryer vent pipe, and an opposite end portion extending through and connected to the outer side of the bottom portion of the pan portion;
so that when the short tubular section is fitted closely around the dryer vent pipe, the dryer may be pushed rearwardly laterally and resiliently compressing the sidewall of the pan portion against the wall surrounding the exhaust pipe therein.
2) An apparatus as in claim 1 wherein the short tubular section is adapted to fit around an outside of the dryer vent pipe.
3) An apparatus as in claim 1 wherein the bottom pan portion has a circular peripheral edge portion.
4) An apparatus as in claim 3 wherein the short tubular section is eccentric to the circular wall portion thereof to better accomodate axial misalignment between the vent pipe on the dryer and the exhaust pipe in the wall.
5) An apparatus as in claim 1 wherein the bottom pan portion has a rectangular peripheral edge portion.
6) An apparatus as in claim 5 wherein the short tubular section is connected to one end portion of the rectangular bottom portion of the pan so that connection of the dryer vent and wall exhaust pipes may be facilitated when they are substantially out of axial alignment.
7) An apparatus as in claim 1 wherein the lateral sidewall comprises a resiliently compressible plastic outer portion.
8) An apparatus as in claim 1 wherein the entire lateral sidewall is substantially laterally compressible.
9) An apparatus as in claim 1 wherein the pan portion and tubular section are formed from sheet metal. 20
10) An apparatus as in claim 1 wherein the pan portion and tubular section are integrally formed from plastic.
11) An apparatus as in claim 10 wherein the plastic is semi rigid and wherein the lateral sidewall is compressible and comprises a rib therearound.
12) A method of connecting a vent pipe on a dryer to an exhaust pipe in a wall comprises the following steps:
providing a connection apparatus having a pan portion having a bottom side portion having a peripheral edge portion and a lateral sidewall connected around and extending away from the peripheral edge portion and an inner side of the bottom portion, said lateral sidewall adapted to laterally and resiliently compress; and, a short tubular section having one end portion adapted to fit closely together with the dryer vent pipe, and an opposite end portion extending through and connected to the outer side of the bottom portion of the pan portion;
closely fitting the short tubular section around the dryer vent pipe; and,
pushing the dryer rearwardly against the wall axially compressing the sidewall around the exhaust pipe therein.
13) A method as in claim 12 further comprising the step of axially twisting the apparatus on the dryer vent pipe to ensure the enclosure of the exhaust pipe in the wall when the dryer is pushed rearwardly.
14) A method as in claim 13 further comprising the step of screwing the apparatus to the dryer to ensure connection thereto in correct position is maintained.