International Journal of Recent Advances in Signal & Image Processing [ISSN: 2581-477X (online)]

A FACE RECOGNITION APPROACH FOR SECURITY APPLICATIONS USING INTERNET OF THINGS

PRAMOD SINGH RATHORE

Lately, the security comprises the most vital segment for people. Right now, expense was most noteworthy reason. Anormous framework was valuable in terms of lessening expense for observing development of outer area. Here, a realtime acknowledgment framework is suggested that will prepare for dealing with pictures in all respects rapidly. The principle target of our proposed mechanism is to ensure home, office with help of perceiving individuals. For such reason, the PIR sensor is utilized for identify development on particular territory. A short time later, the Raspberry Pi will catch the pictures. At that point, the face will be identified and perceived in the caught picture. At long last, the pictures and warnings that are transferred to a cell phone dependent IoT in utilizing Telegram application. Our proposed work framework was constant, quick as well as having less device performing capacity. The test analysis demonstrates that the proposed methodology was acknowledgment framework which can utilize on ongoing framework.

IMAGE MANIPULATION AND DETECTION

SURANJOY LODH

Digital images have been used in a growing number of applications as it has experienced tremendous growth in recent decades. Nowadays, several
softwareâ€™s are available that are used to manipulate image so that the image looks like as original. Images are used as authenticated proof for any crime
and if these images do not remain genuine then it will create a problem. Detecting these types of forgeries has become serious problem at present.
Concurrent with the rapid development of computers and computer programmers is the growing risk that pictures-particularly photographs-will
lose their traditional credibility as it becomes easier to manipulate them as well as our perception of their contents. It is often impossible to see whether
a picture is manipulated or authentic. This paper presents a discussion about the design of classifiers between doctored and original images and discussion
on some of the image manipulation detection techniques for the better approach for its future research.

A REVIEW ON BIOMETRIC SECURITY SYSTEM: FINGERPRINT RECOGNITION AND SPEECH RECOGNITION TECHNOLOGY

SANJULA CHATTERJEE

Biometric is the science and technology of measuring and analysing physical characteristics of a person such as DNA, eye retina, iris, fingerprints, hand
measurement, facial pattern, voice pattern etc. There are so many systems available for but that systems are not so reliable. Of all these systems,
fingerprint biometric system is the most widely used because of its low cost, high efficiency, high matching speed, and relatively high matching accuracy.
Fingerprint biometric system in verifying a legitimate user, numerous government and private organizations are using this system for security
purpose. Speech recognition systems are the efficient alternatives for devices where typing becomes difficult. With growth in the needs for embedded
computing and the demand for emerging embedded platforms, it is required that the speech recognition systems (SRS) are available on them too. This
paper focuses on fingerprint recognition and speech recognition. In this survey we present an overview of various biometric methods for security, its
utilization, challenges, opportunities and introduces the resent issues underlying the biometrics.

CLASSIFICATION OF MAMMOGRAM IMAGES

THIRUMALA LAKSHMI K

Breast cancer is the most dangerous and incurable disease for women. Detecting breast cancer in early stages may increase the women life span. But it is not easy to identify the microcalcification in mammogram images because of its tiny size. In this paper, an author attempted to classify the mammogram images into cancer and non-cancer images by extracting low-level features. The extracted features are classified by a neural network and the SVM classifier. The neural network and the SVM classifier are trained by 150 images and tested by 50 images. The neural network accuracy is based on the mean square error and the regression analysis of the network. If the mean square error and the regression of the neural network attain low-value means, the accuracy of the network is high. Similarly, precision and recall are responsible for the SVM classifier. The database used here is the MIAS database.