Abstract

Fish recognition and classification are challenging when performed on video data obtained in non-controlled environments (NCE’s) such as in natural waters. Many NOAA Fisheries surveys use underwater cameras to gather video data for this purpose, which facilitate the analysis of fish populations. Since the amount of data is large, manual data analysis is insufficient. Automatic processing tools are necessary. Most techniques that extract features from fish are in two categories. In the first, features are specific to fish but not necessarily to a particular species. Yet, such measurements are often unreliable when extracted from video obtained in NCE’s, since they strongly depend on the aspect of fish with respect to the camera. In the second, features are generic and may include texture and shape descriptors. Such features do not target specific species of interest. In this paper, we present an automatic technique using Gabor filters to extract characteristic features from two important species, namely, Epinephelus morio (which has a vertical band located at the tale) and Ocyurus chrysurus (which has a long horizontal line that runs across the body). The proposed algorithm is tested on 200 frames, each containing several fish and non-fish regions. The detection rate is 70.6% for Epinephelus morio and 80.3% for Ocyurus chrysurus, while 23.5% of the undetected Epinephelus morio cases do not have a visible tail band, and 16.7% of the undetected Ocyurus chrysurus cases do not have a visible straight body line. The false alarm rates are 3.8% and 2.1%, respectively.

PDF Preview