Nay Chi Lynn - Academia.edu (original) (raw)

Papers by Nay Chi Lynn

2019 International Conference on Advanced Information Technologies (ICAIT)

Melanoma classification on dermoscopy skin images is a demanding work as a result of the low cont... more Melanoma classification on dermoscopy skin images is a demanding work as a result of the low contrast of the lesion images, the intra-structural variants of melanomas, the much visually likeliness level of whether melanoma or non-melanoma lesions, and the covering of hair and ruler marker artifacts. In this study, the malignant melanoma skin cancer classification system is proposed with the aid of correctly classify melanoma skin cancer. The system involves three main steps: segmentation, feature extraction and classification. Ahead of the segmentation process, the preprocessing skin lesion images is processed for getting rid of the covered hair artifacts. In the segmentation step, the input preprocessed lesion image is segmented by using the proposed texture filter-based segmentation method. Then, the extraction of features with the underlying ABCD (Asymmetry, Border, Color, Differential Texture) dermatology rules using shape, edge, colored and textural features are computed from the segmented region. Lastly, the extracted features are classified to identify if the skin image is malignant melanoma or non-melanoma with the use of bag tree ensemble classifier. The system performance is evaluated with the use of the benchmarking datasets: PH2 dataset, ISBI2016 dataset and ISIC2017 dataset. According to the experimental results, the proposed design allows for both reliable classification of real world dermoscopy images and feasible operation time with today’s standard PC computing platforms. To address the class imbalance in the dataset and to yield the improved classification performance, the experiments are also analyzed not only on original imbalanced dataset but also on balancing datasets: undersampled and oversampled datasets. The system works well and provides both high sensitivity and specificity according to the experimental results on the oversampled dataset with bag tree ensemble classifier to leading to statistically better performance compared to original imbalanced dataset.

2017 18th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT), 2017

Melanoma, one type of skin cancer is considered o the most dangerous form of skin cancer occurred... more Melanoma, one type of skin cancer is considered o the most dangerous form of skin cancer occurred in humans. However it is curable if the person detects early. To minimize the diagnostic error caused by the complexity of visual interpretation and subjectivity, it is important to develop a technology for computerized image analysis. This paper presents a methodological approach for the classification of pigmented skin lesions in dermoscopic images. Firstly, the image of the skin to remove unwanted hair and noise, and then the segmentation process is performed to extract the affected area. For detecting the melanoma skin cancer, the meanshift algorithm that segments the lesion from the entire image is used in this study. Feature extraction is then performed by underlying ABCD dermatology rules. After extracting the features from the lesion, feature selection algorithm has been used to get optimized features in order to feed for classification stage. Those selected optimized features are classified using kNN, decision tree and SVM classifiers. The performance of the system was tested and compare those accuracies and get promising results.

Now a day, there is a need to do research in abandoned object detection due to increase in attack... more Now a day, there is a need to do research in abandoned object detection due to increase in attack by terrorists or anti social elements at public places. The traditional way to observe the places or to track the places is the CCTV cameras which require a human operator to monitor the digital camera images. Although public areas are observed by many surveillance cameras, humans can monitor a few cameras at a time. In real world monitoring applications, abandoned object detection remains to be a challenging task due to factors such as background complexity, illumination variations, noise, and occlusions and "ghost" effect which is left by the removed object. As a fundamental first step in many computer vision applications such as object tracking, behavior understanding, object or event recognition, and automated video surveillance, various algorithms have been developed ranging from simple approaches to more sophisticated ones. In this paper, the study on the different methods proposed so far for detecting the abandoned object in the surveillance area is provided.

Making use of search engines is most popular Internet task apart from email. Currently, all major... more Making use of search engines is most popular Internet task apart from email. Currently, all major search engines employ web crawlers because effective web crawling is a key to the success of modern search engines. Web crawlers can give vast amounts of web information possible to explore the web entirely by humans. Therefore, crawling algorithms are crucial in selecting the pages that satisfy the users’ needs. Crawling cultural and/or linguistic specific resources from the borderless Web raises many challenging issues. This paper will review various web crawlers used for searching the web while also exploring the use of various algorithms to retrieve web pages. Keyword: Web Search Engine, Web Crawlers, Web Crawling Algorithms.

Reverse image search is content-based image retrieval (CBIR) query technique which involves provi... more Reverse image search is content-based image retrieval (CBIR) query technique which involves providing the CBIR system with a sample query image then it will base its search upon. Reverse image search can be used to search either data related to the query image or the images related to that image or similar images or exact images. In this study, different features like color, texture, shape, and neuro fuzzy and different techniques like compact composite descriptor, fractal image processing, and genetic algorithm have been reviewed. Different World Wide Web reverse image search engines (Google, Bing, Tineye) that are available and well-known today are also reviewed.

Proceedings of International Conference on Artificial Life and Robotics, 2017

Body Condition Score (BCS) of a dairy cow is a magnificent indicator for determining energy reser... more Body Condition Score (BCS) of a dairy cow is a magnificent indicator for determining energy reserves of cows. The purpose of this study is to assess BCS of dairy cattle by analyzing cows' rear-view images. In order to do so, we first model shape of cow's tailhead area by using active shape model. Then, angle features are modelled as multiple regression model for estimating scores. The experimental results show that proposed system is promising compared to some existing methods.

Frequent itemsets mining plays an important part in many data mining tasks. This technique has be... more Frequent itemsets mining plays an important part in many data mining tasks. This technique has been used in numerous practical applications, including market basket analysis. This paper presents mining frequent itemsets in large database of medical sales transaction by using the advanced partition approach. This advanced partition approach executes in two phases. In phase 1, the advanced partition approach logically divides the database into a number of non-overlapping partitions. These partitions are considered one at a time and all local frequent itemsets for those partitions are generated using the apriori method. In phase 2, the advanced partition approach finds the final set of frequent itemsets. The purpose of this paper is to extract the final sets of frequent itemsets from medical retail datasets and to support efficient information used to plan marketing or advertising strategies for medical stores and companies. Algorithms for finding frequent itemsets like Apriori, needs many database scans. But, this advanced partition approach needs to scan the entire database only one time. So, it reduces the time taken for the large database scan in mining frequent itemsets.

2017 18th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD), 2017

The Body Condition Score (BCS) is the level of energy reserves in many species, including dairy c... more The Body Condition Score (BCS) is the level of energy reserves in many species, including dairy cattle. For the exact management on dairy farms, the judgment process of BCS is critically important. In this study, the implementation of newly developed approach to estimate body condition score is proposed. Back view images of the cow were used in this system. The area around the tailhead and left and right hooks are segmented automatically and then classified that region for estimating the body condition score. The three main steps conducted are (1) segmentation of cows' images, (2) extraction of region of interest (ROI) by using the convex hull method, and (3) calculation of parameter using moving average method. To confirm this new approach, back view images of various cow types are used and the experimental results confirm its effectiveness with accurate results.

2019 International Conference on Advanced Information Technologies (ICAIT)

Melanoma classification on dermoscopy skin images is a demanding work as a result of the low cont... more Melanoma classification on dermoscopy skin images is a demanding work as a result of the low contrast of the lesion images, the intra-structural variants of melanomas, the much visually likeliness level of whether melanoma or non-melanoma lesions, and the covering of hair and ruler marker artifacts. In this study, the malignant melanoma skin cancer classification system is proposed with the aid of correctly classify melanoma skin cancer. The system involves three main steps: segmentation, feature extraction and classification. Ahead of the segmentation process, the preprocessing skin lesion images is processed for getting rid of the covered hair artifacts. In the segmentation step, the input preprocessed lesion image is segmented by using the proposed texture filter-based segmentation method. Then, the extraction of features with the underlying ABCD (Asymmetry, Border, Color, Differential Texture) dermatology rules using shape, edge, colored and textural features are computed from the segmented region. Lastly, the extracted features are classified to identify if the skin image is malignant melanoma or non-melanoma with the use of bag tree ensemble classifier. The system performance is evaluated with the use of the benchmarking datasets: PH2 dataset, ISBI2016 dataset and ISIC2017 dataset. According to the experimental results, the proposed design allows for both reliable classification of real world dermoscopy images and feasible operation time with today’s standard PC computing platforms. To address the class imbalance in the dataset and to yield the improved classification performance, the experiments are also analyzed not only on original imbalanced dataset but also on balancing datasets: undersampled and oversampled datasets. The system works well and provides both high sensitivity and specificity according to the experimental results on the oversampled dataset with bag tree ensemble classifier to leading to statistically better performance compared to original imbalanced dataset.

2017 18th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT), 2017

Melanoma, one type of skin cancer is considered o the most dangerous form of skin cancer occurred... more Melanoma, one type of skin cancer is considered o the most dangerous form of skin cancer occurred in humans. However it is curable if the person detects early. To minimize the diagnostic error caused by the complexity of visual interpretation and subjectivity, it is important to develop a technology for computerized image analysis. This paper presents a methodological approach for the classification of pigmented skin lesions in dermoscopic images. Firstly, the image of the skin to remove unwanted hair and noise, and then the segmentation process is performed to extract the affected area. For detecting the melanoma skin cancer, the meanshift algorithm that segments the lesion from the entire image is used in this study. Feature extraction is then performed by underlying ABCD dermatology rules. After extracting the features from the lesion, feature selection algorithm has been used to get optimized features in order to feed for classification stage. Those selected optimized features are classified using kNN, decision tree and SVM classifiers. The performance of the system was tested and compare those accuracies and get promising results.

Now a day, there is a need to do research in abandoned object detection due to increase in attack... more Now a day, there is a need to do research in abandoned object detection due to increase in attack by terrorists or anti social elements at public places. The traditional way to observe the places or to track the places is the CCTV cameras which require a human operator to monitor the digital camera images. Although public areas are observed by many surveillance cameras, humans can monitor a few cameras at a time. In real world monitoring applications, abandoned object detection remains to be a challenging task due to factors such as background complexity, illumination variations, noise, and occlusions and "ghost" effect which is left by the removed object. As a fundamental first step in many computer vision applications such as object tracking, behavior understanding, object or event recognition, and automated video surveillance, various algorithms have been developed ranging from simple approaches to more sophisticated ones. In this paper, the study on the different methods proposed so far for detecting the abandoned object in the surveillance area is provided.

Making use of search engines is most popular Internet task apart from email. Currently, all major... more Making use of search engines is most popular Internet task apart from email. Currently, all major search engines employ web crawlers because effective web crawling is a key to the success of modern search engines. Web crawlers can give vast amounts of web information possible to explore the web entirely by humans. Therefore, crawling algorithms are crucial in selecting the pages that satisfy the users’ needs. Crawling cultural and/or linguistic specific resources from the borderless Web raises many challenging issues. This paper will review various web crawlers used for searching the web while also exploring the use of various algorithms to retrieve web pages. Keyword: Web Search Engine, Web Crawlers, Web Crawling Algorithms.

Reverse image search is content-based image retrieval (CBIR) query technique which involves provi... more Reverse image search is content-based image retrieval (CBIR) query technique which involves providing the CBIR system with a sample query image then it will base its search upon. Reverse image search can be used to search either data related to the query image or the images related to that image or similar images or exact images. In this study, different features like color, texture, shape, and neuro fuzzy and different techniques like compact composite descriptor, fractal image processing, and genetic algorithm have been reviewed. Different World Wide Web reverse image search engines (Google, Bing, Tineye) that are available and well-known today are also reviewed.

Proceedings of International Conference on Artificial Life and Robotics, 2017

Body Condition Score (BCS) of a dairy cow is a magnificent indicator for determining energy reser... more Body Condition Score (BCS) of a dairy cow is a magnificent indicator for determining energy reserves of cows. The purpose of this study is to assess BCS of dairy cattle by analyzing cows' rear-view images. In order to do so, we first model shape of cow's tailhead area by using active shape model. Then, angle features are modelled as multiple regression model for estimating scores. The experimental results show that proposed system is promising compared to some existing methods.

Frequent itemsets mining plays an important part in many data mining tasks. This technique has be... more Frequent itemsets mining plays an important part in many data mining tasks. This technique has been used in numerous practical applications, including market basket analysis. This paper presents mining frequent itemsets in large database of medical sales transaction by using the advanced partition approach. This advanced partition approach executes in two phases. In phase 1, the advanced partition approach logically divides the database into a number of non-overlapping partitions. These partitions are considered one at a time and all local frequent itemsets for those partitions are generated using the apriori method. In phase 2, the advanced partition approach finds the final set of frequent itemsets. The purpose of this paper is to extract the final sets of frequent itemsets from medical retail datasets and to support efficient information used to plan marketing or advertising strategies for medical stores and companies. Algorithms for finding frequent itemsets like Apriori, needs many database scans. But, this advanced partition approach needs to scan the entire database only one time. So, it reduces the time taken for the large database scan in mining frequent itemsets.

2017 18th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD), 2017

The Body Condition Score (BCS) is the level of energy reserves in many species, including dairy c... more The Body Condition Score (BCS) is the level of energy reserves in many species, including dairy cattle. For the exact management on dairy farms, the judgment process of BCS is critically important. In this study, the implementation of newly developed approach to estimate body condition score is proposed. Back view images of the cow were used in this system. The area around the tailhead and left and right hooks are segmented automatically and then classified that region for estimating the body condition score. The three main steps conducted are (1) segmentation of cows' images, (2) extraction of region of interest (ROI) by using the convex hull method, and (3) calculation of parameter using moving average method. To confirm this new approach, back view images of various cow types are used and the experimental results confirm its effectiveness with accurate results.