Feature Points based Fish Image Recognition

Abstract

We are studying image-based fish identification. Most traditional approaches use a fish image wherein extraction is easy given that the fish region contrasts with a white or uniform background. This research introduces an approach to give several feature points by manual operation. In our proposed approach, we are able to accept fish image with complicated background, including rocky area. Further, to investigate efficient features for fish recognition in image, we define various features, including geometric features, bag of visual words (BoVW) models, and texture features. We collected images comprising 129 fish species under various photographic conditions and applied our proposed method to these images. From our results, we confirmed that a combination of geometric features and BoVW models obtained the highest recognition accuracy.