Department of Computer Sciences

Permanent URI for this collection

https://repository.run.edu.ng/handle/123456789/72

Browse

Browsing Department of Computer Sciences by Author "Ogunde, Adewale Opeoluwa"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    An Adaptive Thresholding Algorithm-Based Optical Character Recognition System for Information Extraction in Complex Images
    (Journal of Computer Science, 2020-06-12) Ogunde, Adewale Opeoluwa
    Extracting texts from images with complex backgrounds is a major challenge today. Many existing Optical Character Recognition (OCR) systems could not handle this problem. As reported in the literature, some existing methods that can handle the problem still encounter major difficulties with extracting texts from images with sharp varying contours, touching word and skewed words from scanned documents and images with such complex backgrounds. There is, therefore, a need for new methods that could easily and efficiently extract texts from these images with complex backgrounds, which is the primary reason for this work. This study collected image data and investigated the processes involved in image processing and the techniques applied for data segmentation. It employed an adaptive thresholding algorithm to the selected images to properly segment text characters from the image’s complex background. It then used Tesseract, a machine learning product, to extract the text from the image file. The images used were coloured images sourced from the internet with different formats like jpg, png, webp and different resolutions. A custom adaptive algorithm was applied to the images to unify their complex backgrounds. This algorithm leveraged on the Gaussian thresholding algorithm. The algorithm differs from the conventional Gaussian algorithm as it dynamically generated the blocksize to apply threshing to the image. This ensured that, unlike conventional image segmentation, images were processed area-wise (in pixels) as specified by the algorithm at each instance. The system was implemented using Python 3.6 programming language. Experimentation involved fifty different images with complex backgrounds. The results showed that the system was able to extract English character-based texts from images with complex backgrounds with 69.7% word-level accuracy and 81.9% character-level accuracy. The proposed method in this study proved to be more efficient as it outperformed the existing methods in terms of the character level percentage accuracy.
  • Thumbnail Image
    Item
    The Design of a Hybrid Model-Based Journal Recommendation System
    (Advances in Science, Technology and Engineering Systems Journal, 2020-12-14) Ogunde, Adewale Opeoluwa
    There is currently an overload of information on the internet, and this makes information search a challenging task. Researchers spend a lot of man-hour searching for journals related to their areas of research interest that can publish their research output on time. In, this study, a recommender system that can assist researchers access relevant journals that can publish their research output on time based on their preferences is developed. This system uses the information provided by researchers and previous authors' research publications to recommend journals with similar preferences. Data were collected from 867 respondents through an online questionnaire and from existing publication sources and databases on the web. The scope of the research was narrowed down to computer science-related journals. A hybrid model-based recommendation approach that combined Content-Based and Collaborative filtering was employed for the study. The Naive Bayes and Random Forest algorithms were used to model the recommender. WEKA, a machine learning tool, was used to implement the system. The result of the study showed that the Naïve Bayes produced a shorter training time (0.01s) and testing time (0.02s) than the Random forest training time (0.41) and testing time (0.09). On the other hand, the classification accuracy of the Random forest algorithm outperformed the naïve Bayes with % correctly classified instance of 89.73 and 72.66; kappa of 0.893 and 0.714; True Positive of 0.897 and 0.727 and ROC area of 0.998 and 0.977, respectively, among other metrics. The model derived in this work was used as a knowledge-base for the development of a web-based application, named "Journal Recommender" which allowed academic authors to input their preferences and obtain prompt journal recommendations. The developed system would help researchers to efficiently choose suitable journals to help their publication quest.
  • Thumbnail Image
    Item
    Hybridized Deep Convolutional Neural Network and Fuzzy Support Vector Machines for Breast Cancer Detection
    (SN Computer Science, 2021-09-15) Ogunde, Adewale Opeoluwa
    A cancerous development that originates from breast tissue is known as breast cancer, and it is reported to be the leading cause of women death globally. Previous researches have proved that the application of Computer-Aided Detection (CADe) in screening mammography can assist the radiologist in avoiding missing breast cancer cases. However, many of the existing systems are prone to false detections or misclassifications and are majorly tailored towards either binary classification or three-class classification. Therefore, this study seeks to develop both two-class and three-class models for breast cancer detection and classification employing a deep convolutional neural network (DCNN) with fuzzy support vector machines. The models were developed using mammograms downloaded from the digital database for screening mammography (DDSM) and curated breast imaging subset CBISDDSM data repositories. The datasets were pre-processed, and features extracted for classification with DCNN and fuzzy support vector machines (SVM). The system was evaluated using accuracy, sensitivity, AUC, F1-score, and confusion matrix. The 3-class model gave an accuracy of 81.43% for the DCNN and 85.00% accuracy for the fuzzy SVM. The first layer of the serial 2-layer DCNN with fuzzy SVM for binary prediction yielded 99.61% and 100.00% accuracy, respectively. However, the second layer gave 86.60% and 91.65%, respectively. This study’s contribution to knowledge includes the hybridization of deep convolutional neural network with fuzzy support vector machines to improve the detection and classification of cancerous and non-cancerous breast tumours in both binary classification and three-class classification scenarios.