Claim Missing Document
Check
Articles

Found 6 Documents
Search

You only look once model-based object identification in computer vision Reddy, Shiva Shankar; Maheswara Rao, Venkata Rama; Voosala, Priyadarshini; Nrusimhadri, Silpa
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 1: March 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i1.pp827-838

Abstract

You only look once version 4 (YOLOv4) is a deep-learning object detection algorithm. It is used to decrease parameters and simplify network structures, making it suited for mobile and embedded device development. The YOLO detector can foresee an object's Class, bounding box, and probability of that Object's Class being found inside that bounding box. A probability value for each bounding box represents the likelihood of a given item class in that bounding box. Global features, channel attention, and special attention are also applied to extract more compelling information. Finally, the model combines the auxiliary and backbone networks to create the YOLOv4's entire network topology. Using custom functions developed upon YOLOv4, we get the count of the objects and a crop around the objects detected with a confidence score that specifies the probability of the thing seen being the same Class as predicted by YOLOv4. A confidence threshold is implemented to eliminate the detections with low confidence. 
Methodology for eliminating plain regions from captured images Reddy, Shiva Shankar; Gupta, Vuddagiri MNSSVKR.; Srinivas, Lokavarapu V.; Swaroop, Chigurupati Ravi
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 2: June 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i2.pp1358-1370

Abstract

Finding relevant content and extracting information from images is highly significant. Still, it may be challenging to do so because of changes within the textual contents, such as typefaces, size, line orientation, sophisticated backgrounds in images, and non-uniform illuminations. Despite these challenges, extracting content from captured images is still very important. Proficient textual content image recognition abilities extract text from the images to get over these issues. Despite the availability of several optical character recognition (OCR) techniques, this issue has yet to be resolved. Captured images with text are a rich source of information that should be presented so that viewers may make informed decisions. Because of this, it has become a complicated process to extract the text from an image because the text might be of poor quality, has a variety of fonts and styles, and occasionally have a complicated backdrop, among other things. Several approaches have been tried. However, finding a solution remains challenging. The maximally stable external regions (MSER) approach is developed to identify the text region in a picture. MSER is utilized to elevate the plain regions outside the text and non-text areas using geometric features and stroke width variation qualities.
Evaluation of cardiovascular disease in diabetic patients using machine learning techniques Nrusimhadri, Silpa; Swain, Sangram Keshari; Rao, Veeranki Venkata Rama Maheswara; Reddy, Shiva Shankar; Gadiraju, Mahesh
International Journal of Public Health Science (IJPHS) Vol 13, No 3: September 2024
Publisher : Intelektual Pustaka Media Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijphs.v13i3.24213

Abstract

Machine learning (ML) improves operations in many industries, including medicine. It affects the prognosis of several disorders, including heart disease. If predicted, it may provide doctors with new insights and allow them to treat each patient individually. If anticipated, it may provide medical practitioners with valuable information. Our team uses machine learning algorithms to study heart disease risk. This research will compare decision trees, AdaBoost, support vector machines, artificial neural networks (ANN), and customized ANN. The study will include this analysis. The given model will leverage the dataset of general information and medical test results. Our model uses particle swarm optimization (PSO) and k-nearest neighbors (KNN). Algorithm for feature selection. The model reduces dimensionality using evolutionary algorithms and neural networks. We compared the numerous assessment criteria to the current models, our model, and earlier models. Because of this, the suggested model's suitability was rated with the highest accuracy.
Image quality evaluation: evaluation of the image quality of actual images by using machine learning models Reddy, Shiva Shankar; Maheswara Rao, Veeranki V. R.; Sravani, Kalidindi; Nrusimhadri, Silpa
Bulletin of Electrical Engineering and Informatics Vol 13, No 2: April 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v13i2.5947

Abstract

Evaluating image features is a significant step in image processing in applications like number plate detection, vehicle tracking and many image processing-based applications. Image processing-based applications need accurate parts to get the best outcomes. Feature detection is done based on various feature detection techniques. The proposed system aims to get the best feature detector based on the input images by evaluating the image features. For assessing the image features, the proposed system worked on various descriptors like oriented FAST and rotated brief (ORB), learned arrangements of three patch codes (LATCH), binary robust independent elementary features (BRIEF), and binary robust invariant scalable keypoints (BRISK) to extract and evaluate the features using K-nearest neighbor (KNN)-matching and retrieve the inliers of the matching. Each descriptor produces different matching features and inliers; with the matchings and inliers, the inlier ratio calculates to show the analysis. To increase performance, we also examine adding depth information to descriptors.
A novel model to detect and categorize objects from images by using a hybrid machine learning model Sethi, Nilambar; Rama Raju, Vetukuri Venkata Siva; Lokavarapu, Venkata Srinivas; Devareddi, Ravi Babu; Reddy, Shiva Shankar; Nrusimhadri, Silpa
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 1: February 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i1.pp667-679

Abstract

As humans, we can easily recognize and distinguish different features of objects in images due to our brain’s ability to unconsciously learn from a set of images. The objectives of this effort are to develop a model that is capable of identifying and categorizing objects that are present within images. We imported the dataset from Keras and loaded it using data loaders to achieve this. We then utilized various deep learning algorithms, such as visual geometry group (VGG)-16 and a simple net-random forest hybrid model, to classify the objects. After classification, the accuracy obtained by VGG16 and the hybrid model was 84.7% and 89.6%, respectively. Therefore, the proposed model successfully detects objects in images using a simple net as a feature extractor and a random forest for object classification, achieving better accuracy than VGG16.
Evaluation of deep learning models for melanoma image classification Reddy, Shiva Shankar; Rama Raju, Vetukuri Venkata Siva; Swaroop, Chigurupati Ravi; Pilli, Neelima
International Journal of Public Health Science (IJPHS) Vol 12, No 3: September 2023
Publisher : Intelektual Pustaka Media Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijphs.v12i3.22983

Abstract

Melanin-producing cells are the origin of melanoma, the worst form of skin cancer (Melanocytes). If this cancer is not caught early, it might spread to other organs. With automated diagnostic technologies, clinicians and non- professionals may better diagnose diseases. Dermoscopic analysis, biopsy, and histological tests may be needed starting with a clinical assessment. Photo-based skin lesion categorization is challenging due to the fine-grained variability of skin lesions. We provide a more reliable melanoma detection model for each suspicious lesion in this paper. A set of characteristics characterizing a skin lesion's borders, texture, and coloursis used to educate convolutional neural networks. The deep learning models were generated using a standard dataset. To know the model's performance, consider the metrics like accuracy, sensitivity, specificity, Jaccard index and Dice coefficient. Transfer learning is used to categorize normal and diseased skin pictures automatically. This model-driven design helps doctors swiftly assess lesions.