Atul Bansal

Bio: Atul Bansal is an academic researcher from GLA University. The author has contributed to research in topics: Computer science & Iris recognition. The author has an hindex of 10, co-authored 44 publications receiving 383 citations. Previous affiliations of Atul Bansal include Indian Institutes of Technology.

Automatic Detection and Grading of Multiple Fruits by Machine Learning

Abstract: Classification of various types of fruits and identification of the grading of fruit is a burdensome challenge due to the mass production of fruit products. In order to distinguish and evaluate the quality of fruits more precisely, this paper presents a system that discriminates among four types of fruits and analyzes the rank of the fruit-based on its quality. Firstly, the algorithm extracts the red, green, and blue values of the images and then the background of images was detached by the split-and-merge algorithm. Next, the multiple features (30 features) namely color, statistical, textural, and geometrical features are extracted. To differentiate between the fruit type, only geometrical features (12 features), other features are used in the quality evaluation of fruit. Furthermore, four different classifiers k-nearest neighbor (k-NN), support vector machine (SVM), sparse representative classifier (SRC), and artificial neural network (ANN) are used to classify the quality. The classifier has been contemplated with four different databases of fruits: one having 4359 color images of apples; out of which 2342, are with various defects, second having 918 color images of avocado out of which 491 are of with various defects, third having 3805 color images of banana out of which 2224 are with various defects, and fourth having 3050 color images of oranges out of which 1590 are with various defects. The system performance has been validated using the k-fold cross-validation technique by considering different values of k. The maximum accuracy achieved for fruit detection is 80.00% (k-NN), 85.51% (SRC), 91.03% (ANN), and 98.48% (SVM) for k = 10.The classification among Rank1, Rank2, and defected maximum accuracy is 77.24% (k-NN), 82.75% (SRC), 88.27% (ANN), and 95.72% (SVM) achieved by the system. SVM has seen to be more effective in quality evaluation and results obtained are encouraging and comparable with the state of art techniques.

SVM Based Gender Classification Using Iris Images

Abstract: These days biometric authentication systems based on human characteristics such as face, finger, voice and iris are becoming popular among researchers. These systems identify an individual as an authentic or an imposter using a database of enrolled individuals. These systems do not provide other information about imposter such as her gender or ethnicity. Various researchers have utilized facial images for gender classification. Iris images have also been used for identification but there exists a very few references reporting the identification of human attributes such as gender with the help of iris images. In this paper gender has been identified using iris images. Statistical features and texture features using wavelets have been extracted from iris images. A classification model based on Support Vector Machine (SVM) has been developed to classify gender and an accuracy of 83.06% has been achieved in this work.

A comprehensive review on soil classification using deep learning and computer vision techniques

Abstract: Soil classification is one of the major affairs and emanating topics in a large number of countries. The population of the world is rising at a majorly rapid pace and along with the increase in population, the demand for food surges actively. Typical techniques employed by the farmers are not adequate enough to fulfill the increasing requirements and therefore they have to hinder the cultivating soil. For proper crop yield, farmers should be aware of the correct soil type for a particular crop, which affects the increased demand for food. There are various laboratory and field methods to classify soil, but these have limitations like time and labor-consuming. There is a requirement of computer-based soil classification techniques which will help farmers in the field and won’t take a lot of time. This paper talks about different computer-based soil classification practices divided into two streams. First is image processing and computer vision-based soil classification approaches which include the conventional image processing algorithms and methods to classify soil using different features like texture, color, and particle size. Second is deep learning and machine learning-based soil classification approaches, such as CNN, which yields state-of-the-art results. Deep learning applications mostly diminish the dependency on spatial-form designs and preprocessing techniques by facilitating the end-to-end process. This paper also presents some databases created by the researchers according to the objective of the study. Databases are created under different environmental and illumination conditions, using different appliances such as digital cameras, digital camcorder, and a smartphone camera. Also, evaluation metrics are briefly discussed to layout some graded measures for differentiation. This review serves as a brief guide to new researchers in the field of soil classification, it provides fundamental understanding and general knowledge of the modern state-of-the-art researches, in addition to skillful researchers considering some dynamic trends for future work.

Determining diabetes using iris recognition system

Abstract: Iridology is a science which correlates the apparitions of iris to tissue weaknesses in the body. It merely reveals weaknesses, inflammation, or toxicity in organs or tissues. It also indicates weakness long before the symptoms appear. In this paper, support vector machine-based iris recognition system utilizing iridology has been used to determine diabetes. Features from eye image database of 40 people having healthy eye (normal) and having affected eye (diabetes) have been extracted by 2-D wavelet tree. The overall accuracy is obtained to be 87.50 % which reasonably demonstrates the effectiveness of the system.

What Else Does Your Biometric Data Reveal? A Survey on Soft Biometrics

Abstract: Recent research has explored the possibility of extracting ancillary information from primary biometric traits viz., face, fingerprints, hand geometry, and iris. This ancillary information includes personal attributes, such as gender, age, ethnicity, hair color, height, weight, and so on. Such attributes are known as soft biometrics and have applications in surveillance and indexing biometric databases. These attributes can be used in a fusion framework to improve the matching accuracy of a primary biometric system (e.g., fusing face with gender information), or can be used to generate qualitative descriptions of an individual (e.g., young Asian female with dark eyes and brown hair). The latter is particularly useful in bridging the semantic gap between human and machine descriptions of the biometric data. In this paper, we provide an overview of soft biometrics and discuss some of the techniques that have been proposed to extract them from the image and the video data. We also introduce a taxonomy for organizing and classifying soft biometric attributes, and enumerate the strengths and limitations of these attributes in the context of an operational biometric system. Finally, we discuss open research problems in this field. This survey is intended for researchers and practitioners in the field of biometrics.

Visual sensor intelligent module based image transmission in industrial manufacturing for monitoring and manipulation problems

Abstract: Due to technology advancement, smart visual sensing required in terms of data transfer capacity, energy-efficiency, security, and computational-efficiency. The high-quality image transmission in visual sensor networks (VSNs) consumes more space, energy, transmission delay which may experience the various security threats. Image compression is a key phase of visual sensing systems that needs to be effective. This motivates us to propose a fast and efficient intelligent image transmission module to achieve the energy-efficiency, minimum delay, and bandwidth utilization. Compressive sensing (CS) introduced to speedily compressed the image to reduces the consumption of energy, time minimization, and efficient bandwidth utilization. However, CS cannot achieve security against the different kinds of threats. Several methods introduced since the last decade to address the security challenges in the CS domain, but efficiency is a key requirement considering the intelligent manufacturing of VSNs. Furthermore, the random variables selected for the CS having the problem of recovering the image quality due to the accumulation of noise. Thus concerning the above challenges, this paper introduced a novel one-way image transmission module in multiple input multiple output that provides secure and energy-efficient with the CS model. The secured transmission in the CS domain proposed using the security matrix which is called a compressed secured matrix and perfect reconstruction with the random matrix measurement in the CS. Experimental results outwards that the intelligent module provides energy-efficient, secured transmission with low computational time as well as a reduced bit error rate.

Manufacturing intelligent Corvus corone module for a secured two way image transmission under WSN

Abstract: The manufacturing of intelligent and secure visual data transmission over the wireless sensor network is key requirement nowadays to many applications. The two-way transmission of image under a wireless channel needed image must compatible along channel characteristics such as band width, energy-efficient, time consumption and security because the image adopts big space under the device of storage and need a long time that easily undergoes cipher attacks. Moreover, Quizzical the problem for the additional time under compression results that, the secondary process of the compression followed through the acquisition consumes more time.,Hence, for resolving these issues, compressive sensing (CS) has emerged, which compressed the image at the time of sensing emerges as a speedy manner that reduces the time consumption and saves bandwidth utilization but fails under secured transmission. Several kinds of research paved path to resolve the security problems under CS through providing security such as the secondary process.,Thus, concerning the above issues, this paper proposed the Corvus corone module two-way image transmission that provides energy efficiency along CS model, secured transmission through a matrix of security under CS such as inbuilt method, which was named as compressed secured matrix and faultless reconstruction along that of eminent random matrix counting under CS.,Experimental outputs shows intelligent module gives energy efficient, secured transmission along lower computational timing also decreased bit error rate.

Intelligent Secured Two-Way Image Transmission Using Corvus Corone Module over WSN

Abstract: Two-way image communication in a wireless channel needs to be viable with channel properties such as transfer speed, energy-effective, time usage, and security because image capability consumes a huge space in the gadget and is quite effective. Is required in a manner. The figure goes through attacks. In addition, the quiesical issue for additional time of pressure is that the auxiliary interaction of pressure occurs through the dewar receiving extra time. To address these issues, compressed sensing emerges, which packs the image into hours of sensing, is generated in an expedient manner that reduces time usage and saves the use of data transfer capability, however Bomb in transmission. A variety of examinations cleared a way for dealing with security issues in compressive sensing (CS) through giving security as an alternative negotiation. In addition, univariate factors opted for CS as the issue of rearranging image quality is because of the aggregation of clutter. Along these lines related to the above issues, this paper proposed two-way image transmission to the Corvus Coron module, which presents an energy-effective with the CS model, as an inbuilt interaction in the CS transmission through the security framework. Receives what was designated as the pack-protected plot. Impeccable entertainment with the famous arbitrary network conjecture in CS. The result of the test is that the practical module presents energy-efficient and conserved transmission in the form of low error rate with low computational time.

Black-Box vs. White-Box: Understanding Their Advantages and Weaknesses From a Practical Point of View

Abstract: Nowadays, in the international scientific community of machine learning, there exists an enormous discussion about the use of black-box models or explainable models; especially in practical problems. On the one hand, a part of the community defends that black-box models are more accurate than explainable models in some contexts, like image preprocessing. On the other hand, there exist another part of the community alleging that explainable models are better than black-box models because they can obtain comparable results and also they can explain these results in a language close to a human expert by using patterns. In this paper, advantages and weaknesses for each approach are shown; taking into account a state-of-the-art review for both approaches, their practical applications, trends, and future challenges. This paper shows that both approaches are suitable for solving practical problems, but experts in machine learning need to understand the input data, the problem to solve, and the best way for showing the output data before applying a machine learning model. Also, we propose some ideas for fusing both, explainable and black-box, approaches to provide better solutions to experts in real-world domains. Additionally, we show one way to measure the effectiveness of the applied machine learning model by using expert opinions jointly with statistical methods. Throughout this paper, we show the impact of using explainable and black-box models on the security and medical applications.