An Image-based Sea Turtle Identification using Postorbital Facial Feature Points Matching Technique

Abstract

Our natural environment and ecological system has recently become an alarming global concern due to the increase in worldwide pollution levels. Identifying individual wildlife is essential for understanding population and conservation planning. This paper takes this problem into account which focuses on the sea turtle. Traditionally, sea turtle individuals are identified through the application of external flipper tags or internal passive integrated transponders. However, such devices might be lost. This paper proposes a method to perform sea turtle identification using image recognition technique. This idea could be possible because each sea turtle has a unique postorbital facial pattern. To avoid light condition and color problem, we create a mesh of facial pattern, and use it as an image for matching process. The proposed method uses a modification of SIFT feature extraction technique to extract feature vector from the input facial image. The modification of SIFT is proposed to increase robustness against affine transform. The Euclidean distance with Optimize Random Sample Algorithm is used to calculate the matching score. According to the experimental result, the overall accuracy is 99.92%, which shows the good performance of our method.