Abstract -- Robots became not replaceable in the trending world. Each production and manufacturing sectors are in the need of self-modification environment. That will be throughout the world. Latest development in the automation is robots. In research and product technology, the biped robots are used. The step-by-step movement of the robots has been predicted by the desired motors. Objects will be recognized by the sensor placed in the robot. Firstly, the locomotive function of the robots will be designed for the process. Robot walks without direction by using collision avoidance method. The robots for stable walk and place the centre of gravity at a fixed point by helping of Zero moment point. Recognize the objects will be the main theme of the project, various applications can be added for future function. Gait pattern is very important term in the function of robot.

Abstract -- Interpretation of Synthetic Aperture Radar (SAR) images seems to be difficult even for skilled users. This is due to the multiplicative speckle noise from coherent acquisition systems. Therefore, despeckling is expected to play a vital role in the full exploitation of SAR imagery potential. There are many methods using various filters and algorithms which focus on speckle reduction but not all methods can preserve the image features. Thus the proposed method uses an Morphological filter and Hard threshold based wavelet denoising algorithm with block extraction in order to achieve better speckle rejection and detail preservation of edges. The experimental results show that the proposed method has better peak signal to noise ratio than the existing methods.

Abstract -- Fingerprinting is one form of biometrics, a science that can be used for personal identification. It is one of the important techniques and security measures for human authentication across the globe due to its uniqueness and individualistic characteristics. Fingerprints are made up of an arrangement of ridges, called friction ridges. Each ridge consists of pores that are attached to the glands under the skin. Several algorithms proposed different approaches to recreate fingerprint images. However, these works encountered problems with poor quality and presence of structured noise on these images. In this project, we present a novel finger print system that provides more unique and robust algorithms which are capable to distinguish between individuals effectively. A sparse auto encoder (SAE) algorithm is used to reconstruct fingerprint images. It is an unsupervised deep learning model that replicates its input at the output. The sparse auto encoder is a suitable deep learning model to improve the recreation of fingerprint images significantly. The proposed approach showed promising results, and it can enhance the quality of reproduced fingerprint images with a clear ridge structure and eliminating various overlapping patterns.

Abstract -- The proposed model is aimed at detecting intrusions by classifying as benign or malicious in the data set (KDD Cup 99 & CIDCD) has been used to train and test. Then data preprocessing will happen to remove null values and redundancy in the dataset. k means algorithm is used to clustering the dataset into three. Machine learning algorithm called Random Forest algorithm is used to find the accuracy and also to calculate the confusion matrix. Then implemented the deep learning algorithm using Long Short Term Memory algorithm to find the accuracy and also to calculate the confusion matrix. Compare both the accuracy of the Random forest algorithm and Long Short Term algorithm to conclude that the Long Short Term Algorithm is more than Random Forest. Finally send the details of attacked data to the user by email using SMTP.

Abstract -- We should analyze and predict whether given finger print is live or spoofing. It is used to prevent unauthorized access. We have implemented one-class Convolutional Neural Network (CNN), isolation forest and local outlier factor. It provides more accuracy in terms of spoof detection, which is an open-set method. A self-learning, secure and independent open-set solution is essential to be explored to characterize the liveness of fingerprint presentation. Fingerprint spoof presentation classified as live (a Type-I error) is a major problem in a high-security establishment. Type-I error are manifestation of small number of spoof sample. We propose to use only live sample to overcome above challenge. We put forward an adaptive ‘fingerprint presentation attack detection’ (FPAD) scheme using interpretation of live sample. It requires initial high-quality live fingerprint sample of the concerned person. It uses six different image quality metrics as a transient attribute from each live sample and records it as ‘Transient Liveness Factor’ (TLF). Our study also proposes to apply fusion rule to validate scheme with three outlier detection algorithms, one-class Convolutional Neural Network (CNN), isolation forest and local outlier factor. Proposed study got phenomenal accuracy of 100% in terms of spoof detection, which is an open-set method. Further, this study proposes and discusses open issues on person specific spoof detection on cloud-based solutions.