Iris is a physiological biometric trait, which is unique among all biometric traits to recognize personeffectively. In this paper we propose Multi-scale Independent Component Analysis (ICA) based IrisRecognition using Binarized Statistical Image Features (BSIF) and Histogram of Gradient orientation(HOG). The Left and Right portion is extracted from eye images of CASIA V 1.0 database leaving top andbottom portion of iris. The multi-scale ICA filter sizes of 5X5, 7X7 and 17X17 are used to correlate withiris template to obtain BSIF. The HOGs are applied on BSIFs to extract initial features. The final feature isobtained by fusing three HOGs. The Euclidian Distance is used to compare the final feature of databaseimage with test image final features to compute performance parameters. It is observed that theperformance of the proposed method is better compared to existing methods.