Nt1310 Unit 3 Pestle Analysis

, and forehead. The local feature that is mainly used here is wrinkle feature of some particular portions of the face like forehead region, eye corners regions, eyelids, mid of eyebrows. Using five distance values, six features namely feature 1 to feature 6 are calculated in the following way:
Feature 1 = (left to right eye ball distance) / (eye to nose distance)
Feature 2= (left to right eye ball distance) / (eye to lip distance)
Feature 3= (left to right eye ball distance) / (eye to chin distance)
Ranjan Jana et al. / Procedia Computer Science 46 ( 2015 ) 1754 – 1761 1757
Feature 4= (eye to nose distance) / (eye to lip distance)
Feature 5= (eye to nose distance) / (eye to chin distance)
Feature 6= (eye to chin distance) / (virtual top of

Edge detection is widely used for detecting discontinuities in an image. Feature 7 is calculated in following way. The input face image is first converted

Then it passes through canny edge detection technique. It provides a binary image with wrinkle edges as shown in Fig. 4(a). The white pixels of the wrinkle area give information about wrinkle present in the facial image. In binary image, binary value 1 is used for white pixel, and binary value 0 is for black pixel. So, sum of the pixel values of wrinkle area in binary face image is directly proportional to wrinkle present in the face as shown in
Fig. 4(b).
Fig. 4. (a) Edge detected face (b) Edges in wrinkle area
Feature 7= (sum of pixel values in forehead area / number of pixels in forehead area) + (sum of pixel values in left eyelid area / number of pixels in left eyelid area) + (sum of pixel values in right eyelid area / number of pixels in right eyelid area) + (sum of pixel values in left eye corner area / number of pixels in left eye corner area) + (sum of pixel values in right eye corner area / number of pixels in right eye corner area)
Fig. 5. Age vs. Feature 1
Fig. 6. Age vs. Feature