Computer Science and Engineering

Object Recognition, an important task in
image processing and computer vision is not only
concerned with detection and identification of objects
but also content and activity recognition of object in an
image or video sequence. Object recognition is roughly
categorized into two main areas: 1)the task of detecting
the class to which the objects belongs to; which often
employs a learning stage to learn the detector of the
class of interest 2)retrieval of specific object and
matching which corresponds to the matching of object
in question to the model object. This paper surveys
about object recognition system which includes the
main components of a recognition system, its challenges,
goals and application. Also, the two most widely used
matching schemes have been studied.

In this survey paper we have studied and organized the previous works related to machine parts processing using computer vision techniques. The survey mainly focuses on three aspects namely object recognition, defect detection and shape feature extraction. Object recognition can be used in different fields such as industries, robotics, medical diagnosis, video surveillance etc. Defect detection is used in quality control units toremove defective components to maintain the quality of products. Feature extraction begins with data acquisition and builds features they are informative and non-redundant, facilitating the subsequent learning and generalization steps, and in some cases leading to better understanding than human interpretations.

“Visual information plays an major role in computer vision applications”, because an image contains rich amount of
information. In this paper, set of shape signatures that are used for shape based image retrieval by Fourier Descriptor (FD) is
investigated. The shape signatures are one dimensional feature vectors extracted prior to FD is applied. The different
signatures are centroid distance, area function, Angular function, Angular radius function etc. found from existing work. In
addition with existing shape signatures,a new shape signature Multi-Triangle AreaRepresentation (MTAR) proposed in this
paper. The experiments are conducted on MPEG-7 Dataset images. The effectiveness of MTAR is compared with existing
shape signatures and observed that MTAR preserves local and global characteristics of the shape.

Assembly line automation gets more significance to cope up with increasing needs of latest technology machines which are used in industry and society. This paper presents a computationally efficient 2D computer vision based approach to recognize the machine parts and detect damaged parts on the assembly line. The image acquisition system which is part of the assembly line setup acquires data from the moving machine parts in line. Captured machine part image data undergoes image preprocessing techniques like background subtraction, binarization, scaling, and noise and holes removal to transform the data suitable for further processing. Then a contour of the machine parts are extracted and normalized by equal part area method to describe the shape. It gives important clues for machine part shape recognition and defect identification. For experimental purpose a model shape for each machine part is developed, the shape recognition and defect detection are performed with only reference to the model shape. The defects in the machine part such as damage, cracks are identified by the similarity measure between model shape and the data extracted from machine part of the assembly line. The detection and identification of defects at the early stage will helps smooth production process, saves production cost and time.

Advancement in digital technologies have resulted in large amount of images. Hence there a huge demand in retrieving desired images. In order to retrieve an image, the image has to be described or represented by certain features. Shape is an important visual feature of an image. Searching for images using shape features has been an important field of study. There are many shape representation and description techniques in the literature. In this paper, we review one of the important shape descriptor techniques named curvature scale space. The CSS extracts the shape feature of the image and represents them as curvature maxima points. We discuss implementation procedure of this technique, its variants and discuss their advantages and disadvantages.

Simple and fast feature extraction methods are in need today for Content Based Image Retrieval (CBIR) and object recognition applications. The work presented in this paper is contour based one dimensional shape feature extraction technique for closed contour objects. The continuous contour is normalized into 'N' representative points. The sector area based object area normalization (OAN) technique is used for contour normalization. The centroid distance from all normalized points forms 1-D Compact Centroid Distance (CCD) feature vector. The experiments are conducted in MPEG-7 CE Shape-1 Part-B dataset images to test affine invariance property and image retrieval accuracy. Experimental results show the effectiveness of the proposed method in content-based image retrieval tasks.

Shape recognition and retrieval is a complex task on non-rigid objects and it can be effectively performed by using a set of compact shape descriptors. This paper presents a new technique for generating normalised contour points from shape silhouettes, which involves the identification of object contour from images and subsequently the object area normal-isation (OAN) method is used to partition the object into equal part area segments with respect to shape centroid. Later, these contour points are used to derive six descriptors such as compact centroid distance (CCD), central angle (ANG), normalized points distance (NPD), centroid distance ratio (CDR), angular pattern descriptor (APD) and multi-triangle area representation (MTAR). These descriptors are a 1D shape feature vector which preserve contour and region information of the shapes. The performance of the proposed descriptors is evaluated on MPEG-7 Part-A, Part-B and multi-view curve dataset images. The present experiments are aimed to check proposed shape descriptor's robustness to affine invariance property and image retrieval performance. Comparative study has also been carried out for evaluating our approach with other state of the art approaches. The results show that image retrieval rate in OAN approach performs significantly better than that in other existing shape descriptors.

Simple and fast feature extraction methods are in need today for Content Based Image Retrieval (CBIR) and object recognition applications. The work presented in this paper is contour based one dimensional shape feature extraction technique for closed contour objects. The continuous contour is normalized into 'N' representative points. The sector area based object area normalization (OAN) technique is used for contour normalization. The centroid distance from all normalized points forms 1-D Compact Centroid Distance (CCD) feature vector. The experiments are conducted in MPEG-7 CE Shape-1 Part-B dataset images to test affine invariance property and image retrieval accuracy. Experimental results show the effectiveness of the proposed method in content-based image retrieval tasks.

Assembly line automation gets more significance to cope up with increasing needs of latest technology machines which are used in industry and society. This paper presents a computationally efficient 2D computer vision based approach to recognize the machine parts and detect damaged parts on the assembly line. The image acquisition system which is part of the assembly line setup acquires data from the moving machine parts in line. Captured machine part image data undergoes image preprocessing techniques like background subtraction, binarization, scaling, and noise and holes removal to transform the data suitable for further processing. Then a contour of the machine parts are extracted and normalized by equal part area method to describe the shape. It gives important clues for machine part shape recognition and defect identification. For experimental purpose a model shape for each machine part is developed, the shape recognition and defect detection are performed with only reference to the model shape. The defects in the machine part such as damage, cracks are identified by the similarity measure between model shape and the data extracted from machine part of the assembly line. The detection and identification of defects at the early stage will helps smooth production process, saves production cost and time.

Advancement in digital technologies have resulted in large amount of images. Hence there a huge demand in retrieving desired images. In order to retrieve an image, the image has to be described or represented by certain features. Shape is an important visual feature of an image. Searching for images using shape features has been an important field of study. There are many shape representation and description techniques in the literature. In this paper, we review one of the important shape descriptor techniques named curvature scale space. The CSS extracts the shape feature of the image and represents them as curvature maxima points. We discuss implementation procedure of this technique, its variants and discuss their advantages and disadvantages.

Wireless Sensor Networks (WSNs) depicts to the group of spatially distributed sensor nodes, each node is having individual battery for power consumption which senses the factors like Temperature, Pressure, Soil makeup, Vehicular movement, and checks the physical presence of objects, which are communicate through internet and passing messages between nearest neighbor nodes. WSN are extensively used in several applications like Environmental Monitoring, Area Monitoring, Engineering Monitoring, Health Care Monitoring, and Military Applications. Since WSN are highly susceptible for many attacks especially Jamming Attack. This causes high energy consumption, reduces the life time of nodes, affects the entire sensor networks and most significantly also the confidentiality and integrity of the data packets which are transmitted through dissimilar nodes in the network. In order to overcome these issues, a new bio-inspired algorithm called Intelligent Slime Mold (ISM) has been introduced for detection jamming node and to setting up of alternate optimal path form source node to destination node in WSN to avoid jammer affected nodes by applying Context Aware Decision Rule (CADR). This work ensures the confidentiality and integrity of both the network and data packets.

Image memorability is a very hard problem in Image Processing due to its subjective nature. But due to the introduction of Deep Learning and the large availability of data and GPUs, great strides have been made in predicting the memorability of an image. In this paper, we propose a novel deep learning architecture called ResMem-Net that is a hybrid of LSTM and CNN that uses information from the hidden layers of the CNN to compute the memorability score of an image. The intermediate layers are important for predicting the output because they contain information about the intrinsic properties of the image. The proposed architecture automatically learns visual emotions and saliency, shown by the heatmaps generated using the GradRAM technique. We have also used the heatmaps and results to analyze and answer one of the most important questions in image memorability: "What makes an image memorable?". The model is trained and evaluated using the publicly available Large-scale Image Memorability dataset (LaMem) from MIT. The results show that the model achieves a rank correlation of 0.679 and a mean squared error of 0.011, which is better than the current state-of-the-art models and is close to human consistency (p=0.68). The proposed architecture also has a significantly low number of parameters compared to the state-of-the-art architecture, making it memory efficient and suitable for production.

Shape recognition and retrieval is a complex task on non-rigid objects and it can be effectively performed by using a set of compact shape descriptors. This paper presents a new technique for generating normalised contour points from shape silhouettes, which involves the identification of object contour from images and subsequently the object area normalisation (OAN) method is used to partition the object into equal part area segments with respect to shape centroid. Later, these contour points are used to derive six descriptors such as compact centroid distance (CCD), central angle (ANG), normalized points distance (NPD), centroid distance ratio (CDR), angular pattern descriptor (APD) and multi-triangle area representation (MTAR). These descriptors are a 1D shape feature vector which preserve contour and region information of the shapes. The performance of the proposed descriptors is evaluated on MPEG-7 Part-A, Part-B and multi-view curve dataset images. The present experiments are aimed to check proposed shape descriptor's robustness to affine invariance property and image retrieval performance. Comparative study has also been carried out for evaluating our approach with other state of the art approaches. The results show that image retrieval rate in OAN approach performs significantly better than that in other existing shape descriptors.

This study presents a comprehensive analysis of company registration trends in India, focusing on data sourced from the Registrar of Companies (RoC). The study investigates the temporal patterns of company registrations, emphasizing principal business activities and classifications into public and private sectors. Leveraging advanced data pre-processing techniques, The Study explores the spatial and temporal dynamics of company registrations. Furthermore, a suite of machine learning algorithms, including Linear regression, Decision tree, Random Forest, GBM, SVM, KNN, Naive Bayes, and Weka, is employed to predict future registration trends. Visualization of insights is facilitated through the use of Tableau. The findings provide valuable insights for stakeholders in business, policy, and investment sectors, aiding informed decision-making and strategic planning.