Ashim Saha

Study of Implementing Automated Attendance System Using Face Recognition Technique

Authentication is a significant issue in system control in computer based communication. Human face recognition is an important branch of biometric verification and has been widely used in many applications, such as video monitor system, human-computer interaction, and door control system and network security. This paper describes a method for Students Attendance System which will integrate with the face recognition technology using Personal Component Analysis (PCA) algorithm. The system will record the attendance of the students in class room environment automatically and it will provide the facilities to the faculty to access the information of the students easily by maintaining a log for clock-in and clock-out time.

An improved data security using DNA sequencing

Data security is one of the most significant concerned areas of communications and data transmission. The concept of making secure data is to transform a plain message that is understandable by everyone into a human unreadable format or difficult to make out by encoding message using some cryptographic algorithms. Now a day, security is one of the most significant and fundamental issues of data transmission, researchers are working on the evolvement of new cryptographic algorithms. Cryptography is the process of providing security in data while transmitting over public networks by encrypting the original data or message. Data security is concerned with the areas of communication and data transmission. An efficient direction of achieving data security can be termed as DNA based Cryptography. The encryption and decryption process proposed in this paper will use the DNA sequencing string of the DNA strands. We have proposed here how the DNA sequencing can be utilized in cryptographic algorithms and how the message can be made more secure and reliable for transmitting effectively through networks. The algorithm we have proposed here is a new algorithm which has three keys for encrypting the message along with a new method of key generation and key sharing for better security aspects. The cipher text generated by the algorithm is looks similar with the bio-logical structure of the DNA strands. Unnecessary bits are padded with the cipher text in order to make it more complex to the intruders. The encryption algorithm is designed here by using the property of DNA sequencing.

Static and dynamic software metrics complexity analysis in regression testing

In maintenance, assuring code quality and operation, software metrics is widely used by the various software organizations. Software metrics quantify different types of software complexity like size metrics, control flow metrics and data flow metrics. These software complexities must be continuously calculated, followed and controlled. One of the main objectives of software metrics is that measures static and dynamic metrics analysis. It is always considered that high degree of complexity in a fragment is bad in comparison to a low degree of complexity in a fragment. Software metrics can be used in different phases of the software lifecycle. In this paper we will discuss the different metrics and comparison between both static and dynamic metrics. We try to evaluate and analyze different aspects of software static and dynamic metrics in regression testing which offers of estimating the effort needed for testing.

A comparative study on different approaches of real time human emotion recognition based on facial expression detection

Facial Expression Recognition lies in one of the crucial areas of research for human-computer interaction and human emotion identification. For a system to recognize a facial expression it needs to come across multiple variability of human face like color, texture, posture, expression, orientation and so on. The first step to recognize a facial expression of a person with various facial movements of the muscles beneath the eyes, nose and lips are to be detected and further classifying those features by comparing them with a set of trained data values using a good classifier for recognizing the emotion. In this paper a comparative study of the different approaches initiated for automatic real-time facial expression recognition is undertaken along with their benefits and flaws which will further help in developing and improving the system.

An expert system to distinguish a defective eye from a normal eye

Eyes are the organs of vision. Detection of most common differentiating characteristics of eye diseases from the fundus images of the retina can be a good approach as an automatic and low-cost method for broad-classification initial screening. For example in early diabetic retinopathy detection enables application of modern treatment in order to prevent or delay the loss of vision. The paper has referenced Diabetic retinopathy and Retinitis pigmentosa for analysis purpose. Automated approach for detection of microaneurysms in digital color retinal fundus photographs helps ophthalmologist to detect the emergence of its initial symptoms and determine the next immediate action step for the patient. A similar mechanism for automated early disease detection method is proposed featuring identification of dark pigments like minute features, exudate and microaneurysm detection and these features extracted can prove to a greater extent as primary instances for defectiveness of eye. A good number of images along with the response from the ophthalmologist has proved to be a great help towards the observation as derived from this mechanism and discussed in the paper. The proposed mechanism can be extended up to the limit of supervised learning so as to automate the practical responses as obtained from the ophthalmologist in real time scenario.

A Two Round Block Cipher Symmetric Key Cryptography based on Key Stream

Data security is one of the challenges of all times. In the modern computer parlance it is important to secure the vital data. One of the common aspects of data security is the privacy for which Cryptography is the promising methodology. Cryptographic computations can be used in different concerned areas of computer communication for encrypting and transmitting the information. cryptography has shown its effectiveness in the field of secured data transmission and much research work is going on to make the computational process more complex to the unauthorized users so that they cannot decrypt the information in a reasonable time. In this research work, strong substitution based encryption algorithms are proposed and the encryption and decryption process are broadly divided into two rounds and key stream generating procedures are proposed. The proposed procedures are being implemented, analyzed and it shows its efficiency in computation, storage and transmission; and it is more powerful during the decryption process. Proper care has been taken so as to keep the cipher text output file size as close to the plain text file size for fast transmission and besides these the decryption time is more than the encryption time. This paper includes the procedures like Substituent list generation, key generation, encryption and decryption that are continued and enhanced from the previous proposed work [10]. The performances are finally demonstrated and its implementations (using C # language) are explained and analyzed.

A Biometric Based Design Pattern for Implementation of a Security Conscious E-Voting System Using Cryptographic Protocols

With the recent explosion of new technologies in the field of Cryptography, there comes the need for increasing the Security of the present voting system of India. The use of cryptographic protocols as well as biometrics provides a technical response to the security flaws of the current voting system in India. Voting is an instrument of democracy that provides an official mechanism for people to express their views to the government. And e-Voting is considered as one of the most intensely debated subjects in Information Technology. Thus, the voting system should be much more secure and it should also have the stronger authentication mechanism so as to remove fraud and cheats completely from the voting process. This paper proposes and discusses the design of a secure e-voting system based on cryptographic protocols and biometrics that can replace the traditional voting system of India.

An Approach of Extracting Facial Components for Facial Expression Detection using Fiducial Point Detection

Expression detection or Emotion Recognition is one of the rising fields of research on intelligent systems. Emotion plays a significant role in non-verbal communication. An efficient face and facial feature detection algorithms are required to detect emotion at that particular moment. The paperpresents a new approach to the problem of extracting the facial components from a still facial image which will be used further for Facial Expression detection. Robust extraction of such facial feature locations is a crucial problem which is used in a wide range of applications. Facial features such as lip corners, eye corners and nose tip are critical points in a human face. Thepaper approach relies on image segmentation based on skin color algorithm and fiducial point detection. First, the face region is extracted from the image by skin-color filter and window growing. Second, eyes and mouth are approximately located by projection of fiducial point. It is been observed for subjects not wearing glasses, the extraction of eyes could be correctly located in 94% of the images and in over 90% of these images they could be accurately extracted, while for subjects wearing glasses, the success rate is somewhat lower. Also, in certain moods or depending on the facial expression, the detection of lips in case of mouth opening and closing varies which can also be extracted by our method. Keywordsextraction, fiducial point, facial expression.

An Automated Approach to Differentiate a Normal eye from a Defective Eye

Detection of basic differentiating characteristics of eye diseases from the images of the retina can be a good approach as a low-cost method for broad-bas ed initial screening. For example early diabetic retinopathy detection enables application of laser therapy treatment in order to prevent or delay loss of vision. The paper has referenced Diabetic retinopathy and Retinitis pigmentosa for analysis. Automated approach for detection of microaneurysms in digital color fundus photographs helps ophthalmologist to detect the emergence of its initial symptoms and determine the next action step for the patient. A similar mechanism for automated early disease detection method with respect to the features of the normal eye is proposed. The detection algorithm features identification of black pigments like minute features, microaneurysm and exudate detection and these features extracted can prove to a greater extent as ready instances for defectiveness. A number of images along with the feedback and consultation from the ophthalmologist in this area of medical science has proved to be a great help towards the observation as derived from this mechanism and discussed in the later end of this paper. The proposed mechanism can be extended up to the limit of supervised learning so as to automate the practical feedbacks as obtained from the practitioners.