Sukkur IBA Journal of Computing and Mathematical Sciences

Offline English Handwritten Character Recognition using Sequential Convolutional Neural Network

Muhammad Iqbal — 2024-10-10

Handwritten Character recognition falls under the domain of image classification that has been under research for years. The idea is to make the machine recognize handwritten human characters. The language focused in this research paper is English while using offline handwritten character recognition for identifying English characters. There are many publically available datasets from which EMNIST is the most challenging one. The main idea of this research paper is to propose a deep learning CNN method to help recognize English characters. This research paper proposes a deep learning convolutional neural network that is tested and compared with renowned pre-trained models using transfer learning. These parametric settings address multiple issues and are finalized after experimentation. The same hyper-parametric settings were used for all the models under test and E-Character with the same data augmentation settings. The proposed model named the E-Character recognizer was able to produce 87.31% accuracy. It was better than most of the tested pre-trained models and other proposed methods by other researchers. This research paper further highlighted some of the problems like misclassification due to the similar structure of characters.

Comparative Analysis of Pre-trained based CNN-RNN Deep Learning Models on Anomaly-5 Dataset for Action Recognition

Fayaz Ahmed Memon — 2024-10-10

Action recognition in videos is one of the essential, challenging and active area of research in the field of computer vision that adopted in various applications including automated surveillance systems, security systems and human computer interaction. In this paper, we present an in-depth comparative analysis of five CNN-RNN models based on pre-trained networks such as InceptionV3, VGG16, MobileNetV2, ResNet152V2 and InceptionResNetV2 with recurrent LSTM units for action recognition on Anomaly-5 dataset. The performance of these models is analyzed and compared in terms of accuracy, precision, recall & F1-scores and computational efficiency. The CNN-RNN architectures we considered for analysis in this paper, the ResNet152V2 based CNN-RNN model exhibits better performance and achieved highest accuracy, precision, recall and F1-score equal to 92.20% due to its ability to capture more complex spatial features. This comparative analysis may guide the researchers in selecting appropriate models for real-world applications for action recognition. In addition of this, a new dataset is developed called Anomaly-5 that can helps as a valuable resource for training and evaluating action recognition algorithms.

Design and Development of an Acoustic-Based Recongnition System Using DNN

Bushra Jamil — 2024-11-26

Automatic speech recognition is a process of using computers to convert voice signals produced by human speech into reasonable format i.e. text or command that conveys the same meaning as the speaker intended to do. Many researchers are working on various languages including English and other European languages like Spanish, German, and French etc. to develop an automated system for speech recognition (ASR). However, researchers on the development of ASR for the Urdu language have put very little effort. We have developed an Urdu speech recognition system using Deep Neural Network (DNN) on our developed corpus that contains some of the most frequently used words in Urdu like digits, season names, and month names. The accuracy rates of our ASR are very encouraging because 72% accuracy is achieved for 26 words and 92% accuracy is achieved separately for names of seasons.