Signature is being widely used as a personal identification or a verification system, which also comes with wide variety of problems which is getting exposed to forgery. Human errors could add more complexity into the process, hence there is always a need for automated system. Verification can be either online or offline-based. Verification can be performed or accomplished in either ways i.e. online-based or offline-based. The online-based works on image which is digitally acquired as signature uses dynamic information of the signature, when the signature is signed. This paper proposes an offline-system which integrates Android, Matlab, Java where the whole algorithm or the heart of the process takes place in Matlab, Java provides the server and android acts as UI interface. For verification, techniques which are based on geometric features and corner features combined with the training of neural network have been used. Several geometric features have been combined which includes Occupancy region, region where Centroid exist, deviation, even pixels Harris and Scale Invariant Feature Transform (SIFT) features and also Kurtosis, Skewness. The proposed methodology technique includes pre-processing of a scanned signature image at the beginning. Neural network is used as a decision maker for real or forged, while the efficiency of correct recognition is around 90.24% with a threshold of genuine at 60%. The simulation shows that the proposed method has a clear discriminative nature between real and forged signatures.