Pub Date : 2023-02-11DOI: 10.1109/ICITIIT57246.2023.10068658
Kainat Khan, R. Katarya
ASD or autism spectrum disorder is a critical neuro-developmental disorder that hinders an individual's capability of social communication and interaction. This disorder has acquired considerable attention and importance due to its ubiquity among individuals covering all the countries worldwide. Individuals with ASD struggles in daily life activities. Detection of autism with the help of medical tests is a tedious and very costly task. However, detection and care of ASD still remains unfamiliar due to inadequate awareness, knowledge among the society, limited number of diagnostic devices and limited verbal therapy services for ASD patients. This paper investigates and displays reviews of various machine learning approaches on extracting useful data associated with distinctive characteristics of ASD such as brain functioning, hyperactivitperactivity, language disability, etc. Current researches reveal that analysis of biological traits by employing machine learning techniques have helped in the progress of early detection of ASD. ABIDE dataset is very much explored for the research in ASD. Additionally, numerous studies for the advancement of tools are still in progression. The presented research work can remarkably aid future studies on machine learning for ASD.
{"title":"Machine Learning Techniques for Autism Spectrum Disorder: current trends and future directions","authors":"Kainat Khan, R. Katarya","doi":"10.1109/ICITIIT57246.2023.10068658","DOIUrl":"https://doi.org/10.1109/ICITIIT57246.2023.10068658","url":null,"abstract":"ASD or autism spectrum disorder is a critical neuro-developmental disorder that hinders an individual's capability of social communication and interaction. This disorder has acquired considerable attention and importance due to its ubiquity among individuals covering all the countries worldwide. Individuals with ASD struggles in daily life activities. Detection of autism with the help of medical tests is a tedious and very costly task. However, detection and care of ASD still remains unfamiliar due to inadequate awareness, knowledge among the society, limited number of diagnostic devices and limited verbal therapy services for ASD patients. This paper investigates and displays reviews of various machine learning approaches on extracting useful data associated with distinctive characteristics of ASD such as brain functioning, hyperactivitperactivity, language disability, etc. Current researches reveal that analysis of biological traits by employing machine learning techniques have helped in the progress of early detection of ASD. ABIDE dataset is very much explored for the research in ASD. Additionally, numerous studies for the advancement of tools are still in progression. The presented research work can remarkably aid future studies on machine learning for ASD.","PeriodicalId":170485,"journal":{"name":"2023 4th International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121001377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-11DOI: 10.1109/ICITIIT57246.2023.10068650
Sweety Kunjachan, Kala S
Classification of leaves play a vital role in agriculture and Ayurveda. Majority of the research in this field depends upon plant morphology. Among the different parts of the plant, leaves are easy to locate, abundant and occur throughout their lifetime. Plant disease detection, weed management and plant deficiency detection are a few research areas that focus on leaf classification. The size, color and shape may vary depending on geographical conditions and seasonal changes. Hence, classification of leaves is a tedious task. Different approaches have been derived in the last few years. In this paper, various state-of-the-art techniques and their challenges are studied in detail. Comparisons of different approaches in terms of accuracy have also been discussed.
{"title":"Approaches for Plant Leaf Classification: A Review","authors":"Sweety Kunjachan, Kala S","doi":"10.1109/ICITIIT57246.2023.10068650","DOIUrl":"https://doi.org/10.1109/ICITIIT57246.2023.10068650","url":null,"abstract":"Classification of leaves play a vital role in agriculture and Ayurveda. Majority of the research in this field depends upon plant morphology. Among the different parts of the plant, leaves are easy to locate, abundant and occur throughout their lifetime. Plant disease detection, weed management and plant deficiency detection are a few research areas that focus on leaf classification. The size, color and shape may vary depending on geographical conditions and seasonal changes. Hence, classification of leaves is a tedious task. Different approaches have been derived in the last few years. In this paper, various state-of-the-art techniques and their challenges are studied in detail. Comparisons of different approaches in terms of accuracy have also been discussed.","PeriodicalId":170485,"journal":{"name":"2023 4th International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125212331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-11DOI: 10.1109/ICITIIT57246.2023.10068626
Ananya Pandey, D. Vishwakarma
Multi-modal sentiment recognition (MSR) is an emerging classification task that aims to categorize sentiment polarities for a given multi-modal dataset. The majority of work done in the past relied heavily on text-based information. However, in many scenarios, text alone is frequently insufficient to predict sentiment accurately; as a result, academics are more motivated to engage in the subject of MSR. In light of this, we proposed an attention-based model for MSR using image-text pairs of tweets. To effectively capture the vital information from both modalities, our approach combines BERT and ConvNet with CBAM (convolution block attention module) attention. The outcomes of our experimentations on the Twitter-17 dataset demonstrate that our method is capable of sentiment classification accuracy that is superior to that of competing approaches.
{"title":"Attention-based Model for Multi-modal sentiment recognition using Text-Image Pairs","authors":"Ananya Pandey, D. Vishwakarma","doi":"10.1109/ICITIIT57246.2023.10068626","DOIUrl":"https://doi.org/10.1109/ICITIIT57246.2023.10068626","url":null,"abstract":"Multi-modal sentiment recognition (MSR) is an emerging classification task that aims to categorize sentiment polarities for a given multi-modal dataset. The majority of work done in the past relied heavily on text-based information. However, in many scenarios, text alone is frequently insufficient to predict sentiment accurately; as a result, academics are more motivated to engage in the subject of MSR. In light of this, we proposed an attention-based model for MSR using image-text pairs of tweets. To effectively capture the vital information from both modalities, our approach combines BERT and ConvNet with CBAM (convolution block attention module) attention. The outcomes of our experimentations on the Twitter-17 dataset demonstrate that our method is capable of sentiment classification accuracy that is superior to that of competing approaches.","PeriodicalId":170485,"journal":{"name":"2023 4th International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"222 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134559151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper proposes a methodology of a search engine system for searching research papers customized to our institute students. Most of the courses are associated with course projects where students face difficulties in finding the best research papers associated with the course. So, here we propose a customized mechanism to search the research papers published by the faculties of the institute. The input for the proposed search engine can either be the course name or the topic itself. We give users two options: search by course name and topic. If the course name is given as input, we get the corresponding keywords for the course, and then we implement semantic similarity on the Author Keywords. If the user searches by topic, we perform semantic similarity using the given topic and the Author Keywords of the research papers. We have also created a web interface using Django.
{"title":"CISER: Customized Institute Specific Search Engine for Retrieving Research Papers","authors":"Shalaka Sankar, Hamna Muslihuddeen, Shreya Ostwal, Pallapothula Sathvika, Anand Kumar Madasamy","doi":"10.1109/ICITIIT57246.2023.10068620","DOIUrl":"https://doi.org/10.1109/ICITIIT57246.2023.10068620","url":null,"abstract":"This paper proposes a methodology of a search engine system for searching research papers customized to our institute students. Most of the courses are associated with course projects where students face difficulties in finding the best research papers associated with the course. So, here we propose a customized mechanism to search the research papers published by the faculties of the institute. The input for the proposed search engine can either be the course name or the topic itself. We give users two options: search by course name and topic. If the course name is given as input, we get the corresponding keywords for the course, and then we implement semantic similarity on the Author Keywords. If the user searches by topic, we perform semantic similarity using the given topic and the Author Keywords of the research papers. We have also created a web interface using Django.","PeriodicalId":170485,"journal":{"name":"2023 4th International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125103837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-11DOI: 10.1109/ICITIIT57246.2023.10068590
S. Vaidya, Sameer Kavthekar, Amit D. Joshi
The agricultural sector contributes to 18.8% of India's Gross Domestic Product (GDP). With the increase in extreme climatic changes and constant deterioration of the quality of yield in the agricultural sector, detecting and treating plant diseases in their early stages is the need of the hour. At present, plant diseases are identified manually by examining them, which increases the time and decreases the efficiency and quality of the yield. This work focuses on providing a feasible solution to the problem of Plant Disease Detection. This work aims to develop a digital solution to this problem by training the fastest single-stage object detection model, YOLOv7, on the labeled PlantDoc Dataset. Since the PlantDoc dataset is small in size, data augmentation is performed. YOLOv7 achieves a significantly higher mean average precision of 71%. The size of the model is 75.1 MB, and the average time taken to detect an irregularity in an image is 6.8 ms. On account of the small size of the model and fast inference time, this model can be used for edge computing on devices such as satellites and drones to increase the yield produced.
{"title":"Leveraging YOLOv7 for Plant Disease Detection","authors":"S. Vaidya, Sameer Kavthekar, Amit D. Joshi","doi":"10.1109/ICITIIT57246.2023.10068590","DOIUrl":"https://doi.org/10.1109/ICITIIT57246.2023.10068590","url":null,"abstract":"The agricultural sector contributes to 18.8% of India's Gross Domestic Product (GDP). With the increase in extreme climatic changes and constant deterioration of the quality of yield in the agricultural sector, detecting and treating plant diseases in their early stages is the need of the hour. At present, plant diseases are identified manually by examining them, which increases the time and decreases the efficiency and quality of the yield. This work focuses on providing a feasible solution to the problem of Plant Disease Detection. This work aims to develop a digital solution to this problem by training the fastest single-stage object detection model, YOLOv7, on the labeled PlantDoc Dataset. Since the PlantDoc dataset is small in size, data augmentation is performed. YOLOv7 achieves a significantly higher mean average precision of 71%. The size of the model is 75.1 MB, and the average time taken to detect an irregularity in an image is 6.8 ms. On account of the small size of the model and fast inference time, this model can be used for edge computing on devices such as satellites and drones to increase the yield produced.","PeriodicalId":170485,"journal":{"name":"2023 4th International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131491410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-11DOI: 10.1109/ICITIIT57246.2023.10068574
A. Chhabra, D. Vishwakarma
Hate content on social media is currently one of the most significant risks, where the victim is either a single individual or a group of people. In the current scenario, online web platforms are one of the most prominent ways to contribute to an individual's opinions and thoughts. Free sharing of ideas on an event or situation also bulks on the web. Information sharing is sometimes a bane for society if primarily used platforms are utilized with some lousy intention to spread hatred for intentionally creating chaos/ confusion among the public. Users take this as an opportunity to spread hate to get some monetary benefits, the detection of which is of paramount importance. This article utilizes the concept of truncated singular value decomposition (SVD) for detecting hate content on the ETHOS (Binary-Label) dataset. Compared with the baseline results, our framework has performed better in various machine learning algorithms like SVM, Logistic Regression, XGBoost, and Random Forest.
{"title":"A Truncated SVD Framework for Online Hate Speech Detection on the ETHOS Dataset","authors":"A. Chhabra, D. Vishwakarma","doi":"10.1109/ICITIIT57246.2023.10068574","DOIUrl":"https://doi.org/10.1109/ICITIIT57246.2023.10068574","url":null,"abstract":"Hate content on social media is currently one of the most significant risks, where the victim is either a single individual or a group of people. In the current scenario, online web platforms are one of the most prominent ways to contribute to an individual's opinions and thoughts. Free sharing of ideas on an event or situation also bulks on the web. Information sharing is sometimes a bane for society if primarily used platforms are utilized with some lousy intention to spread hatred for intentionally creating chaos/ confusion among the public. Users take this as an opportunity to spread hate to get some monetary benefits, the detection of which is of paramount importance. This article utilizes the concept of truncated singular value decomposition (SVD) for detecting hate content on the ETHOS (Binary-Label) dataset. Compared with the baseline results, our framework has performed better in various machine learning algorithms like SVM, Logistic Regression, XGBoost, and Random Forest.","PeriodicalId":170485,"journal":{"name":"2023 4th International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114770267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-11DOI: 10.1109/ICITIIT57246.2023.10068719
Divya P B, T. Johnson, Kannan Balakrishnan
This paper examines the vulnerability of the Sicil-ian Mafia Network to various central-attack strategies. Social Network Analysis tools are proved to be most effective method in understanding and analysing terrorist networks. The fallback strategy is a good option when the critical nodes are protected. We have performed simultaneous and sequential attacks on the network under different attack strategies. This work assesses the effectiveness of fallback strategy on a data set of Sicilian Mafia Network. We analyze two different data sets generated by phone calls and direct meeting between the suspected criminals. The results shows that the phone call networks are very much vulnerable to the fallback strategy while it is not the case in meeting networks.
{"title":"A study of the effectiveness of the Profile Closeness Attack on the Sicilian Mafia Network","authors":"Divya P B, T. Johnson, Kannan Balakrishnan","doi":"10.1109/ICITIIT57246.2023.10068719","DOIUrl":"https://doi.org/10.1109/ICITIIT57246.2023.10068719","url":null,"abstract":"This paper examines the vulnerability of the Sicil-ian Mafia Network to various central-attack strategies. Social Network Analysis tools are proved to be most effective method in understanding and analysing terrorist networks. The fallback strategy is a good option when the critical nodes are protected. We have performed simultaneous and sequential attacks on the network under different attack strategies. This work assesses the effectiveness of fallback strategy on a data set of Sicilian Mafia Network. We analyze two different data sets generated by phone calls and direct meeting between the suspected criminals. The results shows that the phone call networks are very much vulnerable to the fallback strategy while it is not the case in meeting networks.","PeriodicalId":170485,"journal":{"name":"2023 4th International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130017886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-11DOI: 10.1109/ICITIIT57246.2023.10068575
Satishkumar D, Joshua Daniel Raj J, Anoopkumar H S, Chethan D R, Deekshith More B, Kushal A Y
The agricultural products quality is the influential of economy of any country, especially India contributes 20 to 25% of country's GDP from the agricultural sector. Hence the developing of healthy plants leads to good economic growth of the country and less global food problem. If plants are growing in unhealthy condition and it is effected by disease directly decrease in the country's GDP, to prevent this disease by the existing methods is time consuming and not as per the capital of the farmers.so we can make use of image processing and deep learning to discover acquired infections to the plants early stages. Herbs can be visually seen hence it is convenient to apply image processing technique to identify the disease. Herbs were main origin of food on earth. If the plants are periodically effected by infections and disease becomes a big threat. The diagnosis is given to the plants based on the symptoms visually seen. Nowadays negligible preference towards the traditional methods and the technology is grown, switched towards the deep learning process to detect disease and deep learning is the drastic growing technology in image classification problems.
{"title":"Herbs Ailment Diagnosis using AI Techniques for Sustainable Innovation in Agriculture","authors":"Satishkumar D, Joshua Daniel Raj J, Anoopkumar H S, Chethan D R, Deekshith More B, Kushal A Y","doi":"10.1109/ICITIIT57246.2023.10068575","DOIUrl":"https://doi.org/10.1109/ICITIIT57246.2023.10068575","url":null,"abstract":"The agricultural products quality is the influential of economy of any country, especially India contributes 20 to 25% of country's GDP from the agricultural sector. Hence the developing of healthy plants leads to good economic growth of the country and less global food problem. If plants are growing in unhealthy condition and it is effected by disease directly decrease in the country's GDP, to prevent this disease by the existing methods is time consuming and not as per the capital of the farmers.so we can make use of image processing and deep learning to discover acquired infections to the plants early stages. Herbs can be visually seen hence it is convenient to apply image processing technique to identify the disease. Herbs were main origin of food on earth. If the plants are periodically effected by infections and disease becomes a big threat. The diagnosis is given to the plants based on the symptoms visually seen. Nowadays negligible preference towards the traditional methods and the technology is grown, switched towards the deep learning process to detect disease and deep learning is the drastic growing technology in image classification problems.","PeriodicalId":170485,"journal":{"name":"2023 4th International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117093636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-11DOI: 10.1109/ICITIIT57246.2023.10068679
S. Ezhilarasi, P. Umamaheswari, S. Raghavi
The historic paleographic writings that contributes to cultural heritage of India were inscribed on various materials such as stone inscriptions, rock carving, palm manuscripts, pots, coins, copper plates etc. Archaeological departments throughout the world have undertaken massive digitization projects to digitize the historical contents. But it is highly complicated as it involves images with complex backgrounds, noises and various illumination conditions. The paleographic writings are camera captured and processed for recognition of characters. A character recognition system is an inevitable tool to offer global visibility to the paleographic writings. Automatic character recognition is a challenging problem as in the proposed work it needs a cautious blend of image enhancement, patch extraction, feature extraction, classification and recognition techniques. This involves extracting the sequence of image patches and feature vector of the patches using Convolutional Neural Network and feeding the feature vectors using attention mechanism to recognize the character with LSTM model. As paleographic writings have lengthy sequence of characters which requires special attention during character recognition. The proposed work is an attempt to identify and recognize the historical Tamil paleographic writings by extracting the sequence of patches from the image and feeding them into a CNN-LSTM framework. The proposed method mainly consists of pre-processing, feature extraction, and character-level recognition. The LSTM network is built and the sequence of feature vectors is fed to the network and trained. The sequence of characters is recognized. The performance of the proposed method recorded an character recognition accuracy of 97.9%.
{"title":"Recognition of Characters using PCE based Convolutional LSTM Networks from Palaeographic Writings","authors":"S. Ezhilarasi, P. Umamaheswari, S. Raghavi","doi":"10.1109/ICITIIT57246.2023.10068679","DOIUrl":"https://doi.org/10.1109/ICITIIT57246.2023.10068679","url":null,"abstract":"The historic paleographic writings that contributes to cultural heritage of India were inscribed on various materials such as stone inscriptions, rock carving, palm manuscripts, pots, coins, copper plates etc. Archaeological departments throughout the world have undertaken massive digitization projects to digitize the historical contents. But it is highly complicated as it involves images with complex backgrounds, noises and various illumination conditions. The paleographic writings are camera captured and processed for recognition of characters. A character recognition system is an inevitable tool to offer global visibility to the paleographic writings. Automatic character recognition is a challenging problem as in the proposed work it needs a cautious blend of image enhancement, patch extraction, feature extraction, classification and recognition techniques. This involves extracting the sequence of image patches and feature vector of the patches using Convolutional Neural Network and feeding the feature vectors using attention mechanism to recognize the character with LSTM model. As paleographic writings have lengthy sequence of characters which requires special attention during character recognition. The proposed work is an attempt to identify and recognize the historical Tamil paleographic writings by extracting the sequence of patches from the image and feeding them into a CNN-LSTM framework. The proposed method mainly consists of pre-processing, feature extraction, and character-level recognition. The LSTM network is built and the sequence of feature vectors is fed to the network and trained. The sequence of characters is recognized. The performance of the proposed method recorded an character recognition accuracy of 97.9%.","PeriodicalId":170485,"journal":{"name":"2023 4th International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127997630","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Biometric Identification for animals has been an emerging research field in computer vision. Biometric Identification plays an important role in monitoring diseases, vaccination, planning and control of the produce, and also in ownership assignment. There are several Traditional identification methods like the Ear-Tagging, Ear-Notching, Ear-Tattooing, Freeze-Branding, Hot-Branding and Electrical methods using RFID. The Traditional methods have been invasive, easily duplicable. They are also known for their low accuracies in identification as they are vulnerable to losses. A system with better performance is much needed in this field. Visual Animal Biometrics is gaining wide acceptance all over the world as it provides with better results. This paper aims to explain in detail the implementation of a feature extraction technique called KAZE and through experimental analysis show that it performs better than other feature extraction algorithms.
{"title":"Muzzle Based Identification of Cattle Using KAZE","authors":"Kollabathula Kaushik, Duvvuru Jaswanth Reddy, Rahul Raman","doi":"10.1109/ICITIIT57246.2023.10068662","DOIUrl":"https://doi.org/10.1109/ICITIIT57246.2023.10068662","url":null,"abstract":"Biometric Identification for animals has been an emerging research field in computer vision. Biometric Identification plays an important role in monitoring diseases, vaccination, planning and control of the produce, and also in ownership assignment. There are several Traditional identification methods like the Ear-Tagging, Ear-Notching, Ear-Tattooing, Freeze-Branding, Hot-Branding and Electrical methods using RFID. The Traditional methods have been invasive, easily duplicable. They are also known for their low accuracies in identification as they are vulnerable to losses. A system with better performance is much needed in this field. Visual Animal Biometrics is gaining wide acceptance all over the world as it provides with better results. This paper aims to explain in detail the implementation of a feature extraction technique called KAZE and through experimental analysis show that it performs better than other feature extraction algorithms.","PeriodicalId":170485,"journal":{"name":"2023 4th International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"159 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125932333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}