Pigeon Breed Recognition Using Convolutional Neural Network

Abstract

Pigeon farming is a very familiar business as well as a hobby in Bangladesh. It has a great contribution to our national economy. Sometimes it's a very tough job for us to recognize pigeon breed correctly because some breed of pigeons looks similar in human eyes though they are pretty much different. Image classification plays a vital role to identify the Pigeon breed names. Automatic recognition of objects through the computer vision approach is becoming more popular day by day. So our aim is to classify the pigeon breed names. Very few works have been done for pigeon classification. We have employed a deep learning model that trained on the large data set. Our designed system can be scaled to small systems such as handheld devices and large systems such as computer vision models on the cloud. Therefore, both the users like pigeon buyers and the researchers managing the state-of-the-art research works can use this system to accomplish their purposes. We have applied different novel research methods and sophisticated tools to solve the problem of recognition and classification of pigeon breeds. Moreover, this system can be used as a baseline threshold in classification tasks and so future works on such image classification problems can be compared with the performance of this system.