Recent developments in machine learning engendered many algorithms designed to solve diverse problems in countless scientific areas, particularly recognition structures such as speech recognition, text recognition, image recognition. In image recognition tasks, the experiments within limited computing and time constraints are challenging issue. In this paper, we have recognized different types of bird’s images and performance analysis of machine learning algorithms. Basic assembly of support vector machine, k-nearest neighbors, random forest and logistic regression are modified for experiments by defining relationships and adjusting different parameters. We have collected 3490 images of 22 types of bird’s and created our dataset and the dataset is adopted to extract the features and the algorithms are employed for recognition of the different types of bird’s images. The experimental results are discussed in terms of accuracy, Precision, recall and F1 score. While, the support vector machine better preforms as compared to the other three methodologies, whereas, KNN, RF and LR achieved more interesting results.