PakhiChini: Automatic Bird Species Identification Using Deep Learning
Kazi Md Ragib, Raisa Taraman Shithi, Shihab Ali Haq, Md. Mehedi Hasan, Kazi Mohammed Sakib, Tanjila Farah
Abstract
The sector of entire image classification has recently found outstanding accomplishment in Convolutaional Neural Network. Lately, leveraging pretrained Convolutional Neural Networks (CNN) offer a much better illustration of an input image. ResNet [1] is one the top pretrained CNN networks that is mostly used in deep learning as pretrained CNN model. In this paper, we propose a deep learning model that is capable of identifying individual birds from an input image. We tend to additionally leverage pretrained ResNet model as pretrained CNN networks with base model to encode the images. Usually, birds are found in diverse scenarios which are seen in different sizes, shapes, sizes, colors from human point of view. Conducted experiments will be using the entity of different dimensions, cast and celerity to study recognition performance. We achieved a top-5 accuracy of 97.98% on our classifications.