Live shrimp larvae counting method using co-occurrence color histogram

This paper proposes the method of counting numbers of shrimp larvae in water-filled containers using image processing techniques. Images of the containers are captured from a camera over the containers. The images are preprocessed for noise removal and enhancement. The resulting images are then processed to count the number of shrimp larvae with an acceptable accuracy. Our experimental results show that estimates of shrimp larvae numbers with 97% accuracy under controlled conditions. Some issues of system development and practical implementation are discussed.