Proceedings of the First International Conference on Advances in Computer Vision and Artificial Intelligence Technologies (ACVAIT 2022).

Format:

Book

Author/Creator:

Manza, Ramesh.

Contributor:

Gawali, Bharti.

Yannawar, Pravin.

Juwono, Filbert.

Series:

Advances in Intelligent Systems Research Series

Advances in Intelligent Systems Research Series ; v.176

Language:

English

Subjects (All):

Computer vision.

Artificial intelligence.

Physical Description:

1 online resource (746 pages)

Edition:

1st ed.

Other Title:

Proceedings of the First International Conference on Advances in Computer Vision and Artificial Intelligence Technologies

Place of Publication:

2023.

Dordrecht : Atlantis Press (Zeger Karssen), 2023.

Summary:

This volume presents the proceedings from the First International Conference on Advances in Computer Vision and Artificial Intelligence Technologies (ACVAIT 2022) held in Aurangabad, India. The conference, organized by the Department of Computer Science and Information Technology at Dr. Babasaheb Ambedkar University, focused on recent advancements in computer vision, image processing, pattern recognition, artificial intelligence, and machine learning. Contributions from researchers and experts in the field provide insights into topics such as biomedical image processing, remote sensing, and geospatial technology. The book offers a platform for young and experienced researchers to discuss scientific findings and exchange ideas with domain experts, fostering collaboration among academic and industry professionals. It serves as a valuable resource for the scientific community interested in these advanced technologies. Generated by AI.

Contents:

Intro

Preface

Organization

Contents

Peer-Review Statements

1 Review Procedure

2 Quality Criteria

3 Key Metrics

An Improved Computer Aided System for Lung Cancer Detection using Image Processing Techniques

1 Introduction

2 Literature survey

3 Methodology

4 Result

5 Conclusion

References

Automated Detection of Tuberculosis Based on Cantilever Biosensor

2 Bio-Mems Cantilever Sensor

3 Experimental Details

4 Result and Discussion

Diagnosing Microscopic Blood Samples for Early Detection of Leukemia by Deep and Hybrid Learning Techniques

2 Related Work

3 Materials and Methods

3.1 Description of Two Datasets

3.2 Pre-processing

3.3 Convolutional Neural Networks (CNN)

3.4 Hybrid of Deep and Machine Learning

4 Experimental Result

4.1 Splitting Dataset

4.2 Evaluation Metrics

4.3 CNN Models Results

4.4 Results of the Hybrid CNN with SVM Algorithm

5 Discussion

6 Conclusion

Lung Cancer Nodules Detection Using Ideal Features Extraction Technique in CT Images

3 Methods and materials

3.1 Dataset

3.2 Image Preprocessing

3.3 Segmentation

3.4 Feature Extraction

3.5 Classification Using Hybrid-CNN

Fuzzy Level Set Search and Rescue Optimization (FLSSR) Based Segmentation of Pediatric Brain Tumor

3 Proposed Methodology

3.1 Preprocessing

3.2 Fuzzy Level Set Search and Rescue Optimization (FLSSR) for Segmentation Process:

4 Results and Discussions

5 Performance Evaluation

Investigating EEG Images of Cognitive Actions for Robotic Arm

2 Literature Review

3.1 Participants.

3.2 Technical Analysis

3.3 Analyzing .edf Files via EEGLAB

3.4 Robotic Arm Overview

3.5 Active Region Identification

3.6 ERD and ERS for the Components in Frontal Region

4 Performance evaluation of the Robotic Arm

5 Result

Localization of Intervertebral Discs Using Deep-Learning and Region Growing Technique

2 Review of the Literature

3.1 Data

3.3 Proposed Method

4 Results and Discussion

4.1 Evaluation Matrices

4.2 Effect of Hourglass Attention Mechanism

Identification of Skin Disease Using Machine Learning

2 Related Works

3 Method and Techniques

3.1 Input Images

3.3 Filtering Techniques

3.4 Gaussian Filter

3.5 Image Segmentation

3.6 Support Vector Machine (SVM)

3.7 K-nearest Neighbor (KNN)

3.8 Feature Extraction

3.9 Color Moments

3.10 Texture Feature Extraction

4 Performance Measures

5 Result and Discussion

Apple Classification Based on MRI Images Using VGG16 Convolutional Deep Learning Model

2 Literature Survey

3.2 VGG Model

5 Conclusion and Future Work

Design a Novel Detection Using KNN Classification Technique for Early Sign of Diabetic Maculopathy

2 Methodology

2.1 Preprocessing

2.2 RGB Channel

2.3 Histogram

2.4 Enhancement

2.5 KNN Classification

3 Experiment Result

4 Conclusion

Extraction of Bank Cheque Fields Based on Faster R-CNN

2 Related Work and Overview

2.1 Related Work

2.2 Faster RCNN

3.1 ConvNet Layers

3.2 Region Proposal Networks.

3.3 Region of Interest Pooling Layer

3.4 Classification Layers

4 Experiment and Results

4.1 Dataset

4.2 Experiment Results

Multimodal Deep Learning Based Score Level Fusion Using Face and Fingerprint

3 About Database

4 Experimental Setup

5 Proposed Methodology

5.1 Pre-processing

5.2 CNN

5.3 VGG16

5.4 Features Classification

5.5 Score Level Fusion

6 Performance Analysis

6.1 Classification and Confusion Matrix

7 Result and Discussion

8 Conclusion

9 Contributions

Enhanced Technique for Exemplar Based Image Inpainting Method

3.1 Input Image

3.2 Perform Cropping

3.3 Perform Inpainting by Criminisi Method

3.4 Finding Parameters

3.5 Perform Tensor Inpainting

4 Experimental Results

An Optimal (2, 2) Visual Cryptography Schemes For Information Security

5 Discussion and Performance Analysis

5.1 Pixel Expansion

5.2 Contrast and Statistical Analysis

5.3 Mean Square Error

5.4 Peak-Signal-to-Noise-Ratio

5.5 Universal-Index-Quality (UIQ)

5.6 Maximum Difference (MD)

5.7 Average Difference (AD)

A Numeral Script Identification from a Multi-lingual Printed Document Image

1.1 Motivation

2 Proposed Method

3 Experimental Results

A Novel Approach for Object Detection Using Optimized Convolutional Neural Network to Assist Visually Impaired People

3 Architectural Description of the Proposed Object Detection Model for Visually Impaired (ODMVI)

3.2 Segmentation.

3.3 Feature Extraction

4 Optimal Feature Selection

5 Object Detection Using CNN

5.1 Convolution Layer

5.2 Pooling Layer

5.3 Fully Connected Layer

6 Dataset

7 Results and Discussion

7.1 Simulation Procedure

7.2 Convergence Analysis

7.3 Performance Evaluation of ODMVI

8 Conclusion and Future Scope

A Machine Learning Based Approach for Image Quality Assessment of Forged Document Images

3.1 Pre-processing

3.2 Feature Extraction

3.3 Classification

4 Implementation and Results

5 Statistical Test of Significance

Comparative Study of Grid-Inverted List Hybrid Indexing Techniques for Moving Objects and Queries

3.1 Grid-Inverted List Hybrid Index

3.2 KNN Query

3.3 Hybrid Index Implementation with YPK-CNN Technique

3.4 Hybrid Index Implementation with SEA-CNN Technique

3.5 Hybrid Index Implementation with CPM Technique

3.6 Differences Between YPK-CNN, SEA-CNN and CPM Techniques

3.7 Proposed Algorithms

4 Experimental work

5 Results and Discussion

Text-Independent Source Identification of Printed Documents using Texture Features and CNN Model

2 Review of Related Studies

3 Proposed Method

3.1 Data Collection

3.3 Feature Extraction

4 Experimental Results and Discussion

4.1 Performance of Textual Features

4.2 Deep Learning CNN Performance Measurement

4.3 Comparison Analysis

A Vision-Based Sign Language Recognition using Statistical and Spatio-Temporal Features

3.2 Feature Extraction and Learning.

4 Results and Discussion

4.1 Raw Data Pre-processing

4.2 Extraction and Analysis of Statistical and Spatio-Temporal Features

4.3 Classification of Statistical Features

4.4 Early Fusion of Statistical and Spatio-Temporal Features

4.5 Comparison of Results

4.6 Conclusion and Future Work

Single Image Dehazing Using Haze Veil Analysis and CLAHE

3 Haze Veil Calculation

3.1 Computing Reflectance Image

HiTEK Multilingual Speech Identification Using Combinatorial Model

3 Challenges

4 Methodology

4.1 Hidden Markov Model- Gaussian Mixture Model

4.2 Hidden Markov Model- Artificial Neural Networks

4.3 Hidden Markov Model- Deep Neural Networks

4.4 POS Tagging

4.5 Tokenization and Stemming

4.6 Morphological Analysis

4.7 Syntactical Analysis

4.8 Semantic Analysis

4.9 Word Discourse Knowledge

5 Experimental Setup and Results

6 Conclusion and Future Scope

Devanagari License Plate Detection, Classification and Recognition

1.1 Devanagari (Nepalese) License Plate

3.1 LP Detection and Classification

3.2 Character Segmentation and Recognition

4.1 DLP Dataset

4.2 Detection and Classification Results

4.3 Character Recognition Results

4.4 Real-Time Implementation Results

Pre-trained Convolutional Neural Networks for Gender Classification

3.1 Keras Models

3.2 Custom CNN

AVAO Enabled Deep Learning Based Person Authentication Using Fingerprint

2 Motivation.

2.1 Literature Review.

Notes:

Description based on publisher supplied metadata and other sources.

Part of the metadata in this record was created by AI, based on the text of the resource.

ISBN:

9789464631968

9464631961

OCLC:

1396698168