Gait recognition is one of the most recent emerging technique of human biometric which can be used for security based purposes. In comparison with other bio-metric techniques gait analysis has some special security features. Most of the biometric techniques use sequential template based component analysis for recognition. Here we have proposed a developed technique for gait identification using the feature Gait Energy Image (GEI). It is implemented using Kohonen Self-Organizing Mapping (KSOM) neural network. GEI representation of gait contains all information of each image in one complete gait cycle and requires less storage and low processing speed. As only one image is enough to store the necessary information in GEI feature, recognition process is a bit easier than any other feature of gait recognition. Gait recognition has some limitations like viewing angle variation, walking speed, clothes, carrying load etc. Robust View Transformation Model (RVTM) is used to solve the problem of viewing angle. RVTM transforms the viewing angle data from various angle to specific angle. RVTM enhances recognition performance. Our proposed method compares the recognition performance with template based feature extraction which needs to process each frame in the cycle. We use GEI which gives all possible information about all the frames in one cycle and results in better performance than other feature of gait analysis.