Research Article

Face Alignment Algorithm Based on an Improved Cascaded Convolutional Neural Network

Table 1

Design of the CCNN algorithm.

Stage 1Input: X (face images with face frames.)
Step 1: resize X to (39393)
Step 2: after 2 sets of convolutional, pooling layer, and 2 fully connected layers, generate a candidate set of key points
Step 3: same as step 2; generate candidate face key point coordinates
Output: y1 (face image with 5 weighted key points)
Stage 2Input: use 2 different windows with shake to crop y1 to obtain 10 partial face images
Step 1: similar to stage1-step2; generate a candidate set of key points
Step 2: every 2 CNNs colocate a key point
Output: y2 (face image with 5 weighted key points)
Stage 3Input: use 2 smaller different windows with shake to crop y2 to obtain 10 partial face images
Step 1: similar to stage2-step1; generate a candidate set of key points
Step 2: every 2 CNNs colocate a key point
Output: y3 (face image with 5 weighted key points)