Age and gender estimation using a convolutional neural network
A method of age and gender estimation, comprising receiving an input image, detecting a facial image within the input image, estimating a head pose based on a set of facial image intensities of the facial image, wherein the head pose is expressed as a yaw, a pitch and a roll, determining whether the yaw, the pitch and the roll of the head pose is less than a predetermined threshold, aligning the facial image if the yaw, the pitch and the roll of the head pose are less than the predetermined threshold and predicting an age and a gender of the aligned facial image.
1. A method of age and gender estimation, comprising:
receiving an input image;
detecting a facial image within the input image;
estimating a head pose based on a set of facial image intensities of the facial image, wherein the head pose is expressed as a yaw, a pitch, and a roll;
determining whether the yaw, the pitch, and the roll of the head pose is less than a predetermined threshold;
aligning the facial image if the yaw, the pitch, and the roll of the head pose are less than the predetermined threshold; and
predicting au age and a gender of the aligned facial image.
2. The method of age and gender estimation of claim 1 , wherein the alignment of the facial image is performed using five-point facial landmarks.
3. The method of age and gender estimation of claim 1 , wherein the predetermined threshold limits the head pose to near-frontal head poses.
4. The method of age and gender estimation of claim 1 , further comprising extracting features of the aligned facial image.
5. The method of age and gender estimation of claim 1 , wherein the prediction of the age and the gender is performed via a convolutional neural network.
6. The method of age and gender estimation of claim 5 , wherein the convolutional neural network utilized is one of ResNet-50-C4 and EfficientNetB4.
7. The method of age and gender estimation of claim 5 , wherein the convolutional neural network includes a batch normalization, a dropout after the batch normalization, a fully connected layer after the dropout and a second batch normalization.
8. The method of age and gender estimation of claim 5 , wherein the convolutional neural network includes a feature mapping of the aligned facial image, a two-point age distribution within a fully connected layer and a regression layer.
9. The method of age and gender estimation of claim 5 , wherein the convolutional neural network includes a feature mapping of the aligned facial image, a gaussian age distribution within a fully connected layer and a regression layer.
10. The method of age and gender estimation of claim 1 , wherein age estimation is provided as a gaussian distribution.
11. The method of age and gender estimation of claim 1 , wherein the detecting of the facial image is performed using five-point facial landmarks.