OPTIMIZING CNN HYPERPARAMETERS FOR ENHANCED HANDWRITTEN DIGIT RECOGNITION ON CUSTOM DATASET: A SYSTEMATIC STUDY

Handwriting recognition remains a challenge in the machine vision field, especially in optical character recognition (OCR). The OCR has various applications such as the detection of handwritten Farsi digits and the diagnosis of biomedical science. In expanding and improving quality of the subject, this research focus on the recognition of Farsi Handwriting Digits and illustration applications in biomedical science. The detection of handwritten Farsi digits is being widely used in most contexts involving the collection of generic digital numerical information, such as reading checks or digits of postcodes. Selecting an appropriate classifier has become an issue highlighted in the recognition of handwritten digits. The paper aims at identifying handwritten Farsi digits written with different handwritten styles. Digits are classified using several traditional methods, including K-nearest neighbor, artificial neural network (ANN), and support vector machine (SVM) classifiers. New features of digits, namely, geometric and correlation-based features, have demonstrated to achieve better recognition performance. A noble class of methods, known as deep neural networks (DNNs), is also used to identify handwritten digits through machine vision. Here, two types of introduce its expansion form, a convolutional neural network (CNN) and an auto-encoder, are implemented. Moreover, by using a new combination of CNN layers one can obtain improved results in classifying Farsi digits. The performances of the DNN-based and traditional classifiers are compared to investigate the improvements in accuracy and calculation time. The SVM shows the best results among the traditional classifiers, whereas the CNN achieves the best results among the investigated techniques. The ANN offers better execution time than the SVM, but its accuracy is lower. The best accuracy among the traditional classifiers based on all investigated features is 99.3% accuracy obtained by the SVM, and the CNN achieves the best overall accuracy of 99.45%.

Handwritten digit recognition is the intelligence of computers to recognize digits written by humans. But it becomes one of the most challenging tasks for machines as handwritten digits are not perfect and can be made with many different: flavors, size, thickness. Thus, as a solution to this problem, Handwriting digit recognition model comes into picture. Many machine learning techniques have been employed to solve the handwritten digit recognition problem. This paper focuses on Neural Network (NN) approaches. Among the three famous NN approaches: deep neural network (DNN), deep belief network (DBN) and convolutional neural network (CNN), the specialization of CNN as compared to other NN of being able to detect pattern is what makes it so useful for recognizing handwritten digits. Humans can very easily see, read & write any handwritten digits, when written in proper format. Even if the digits are not written in proper format we can use our logic and predict what digit it could be. But It is a hard task for the machine to recognize handwritten digits as these are not perfect and can be made with many different flavors. Thus handwritten digit recognition is the solution to this problem which uses the image of a digit and recognizes the digit present in the image. The handwritten digit recognition is the ability of computers to recognize human handwritten digits. The goal is to build a model that can efficiently and reliably recognize the digits and output the proper result. Amongst all the other neural networks, working and implementing a model using Convolution Neural Network gives out the most precise results. It is most popularly used for analyzing images as well as for other data analysis or classification problems. CNN has hidden layers called convolutional layers. These layers work the same way as other layers do but here we need to specify the no of filters each layer should have These filters are actually what detects the pattern. Patterns could be edges, corners, circles or any complex other objects like eyes, ears or even deeper full dogs, cats, etc. Thus, the specialization of CNN as compared to other NN of being able to detect patterns is what makes it so useful for recognizing handwritten digits Key Word: Neural Networks; Convolutional Neural Networks (CNN); Image Processing; Optical Character Recognition (OCR); MNIST Dataset

Amharic language is the second most spoken language in the Semitic family after Arabic. In Ethiopia and neighboring countries more than 100 million people speak the Amharic language. There are many historical documents that are written using the Geez script. Digitizing historical handwritten documents and recognizing handwritten characters is essential to preserving valuable documents. Handwritten digit recognition is one of the tasks of digitizing handwritten documents from different sources. Currently, handwritten Geez digit recognition researches are very few, and there is no available organized dataset for the public researchers. Convolutional neural network (CNN) is preferable for pattern recognition like in handwritten document recognition by extracting a feature from different styles of writing. In this work, the proposed model is to recognize Geez digits using CNN. Deep neural networks, which have recently shown exceptional performance in numerous pattern recognition and machine learning applications, are used to recognize handwritten Geez digits, but this has not been attempted for Ethiopic scripts. Our dataset, which contains 51,952 images of handwritten Geez digits collected from 524 individuals, is used to train and evaluate the CNN model. The application of the CNN improves the performance of several machine-learning classification methods significantly. Our proposed CNN model has an accuracy of 96.21% and a loss of 0.2013. In comparison to earlier research works on Geez handwritten digit recognition, the study was able to attain higher recognition accuracy using the developed CNN model.

The development of a handwritten digit recognition system is the main subject of the discussion. In particular, the Convolution Neural Network (CNN) technique is used in the proposed topic. The MNIST dataset is used to create the model. The “Modified National Institute of Standards and Technology dataset” has 60,000 grayscale photographs, which are tiny squares, comprises of hand-written single digits between digit Zero and digit Nine and each measuring 28 by 28. Placing a handwritten digit picture among any one of ten classes corresponding to integer values from digit Zero to digit Nine, inclusively is the assignment here. The system employs a camera to take photos made up of images produced by the MNIST test data set and samples supplied by other authors. It then continually processes the images and updates the output every 0.5 seconds. Accuracy for top-performing models is typically 99.

Handwritten digit recognition, a task in computer vision, is critical for applications such as postal automation, banking, and digitization of forms. Traditional approaches have leveraged statistical models, but the rise of deep learning, particularly Convolutional Neural Networks (CNN) and Long-Short Term Memory (LSTM), has revolutionized the field. However, a comprehensive performance comparison of CNN and LSTM architectures in the context of handwritten digit classification remains underexplored. This study aimed to address this gap by evaluating and comparing CNN and LSTM models for the classification of handwritten digits. Two machine learning models – Convolutional Neural Network (CNN) and Long-Short Term Memory (LSTM) were trained with the preprocessed handwritten digit dataset. The CNN model was designed with multiple convolutional and pooling layers, along with dropout for regularization. The LSTM model was designed with LSTM layers to capture sequential patterns in the data, followed by a dense layer for classification. The models were implemented in python, evaluated and compared based on accuracy, precision, recall and F1-score. The evaluation and comparison results indicate that CNN achieved 99.31% accuracy, 99.0% precision, 99.0% recall, and a 99.0% F1-score, while LSTM achieved 98.90% accuracy, 99.0% precision, 99.0% recall, and a 99.0% F1-score. The results demonstrated that CNN outperformed LSTM in terms of accuracy and misclassification errors, making it the optimal choice for image-based handwritten digit recognition. This finding underscores the efficiency of CNN in addressing challenges related to digit recognition, contributing to the advancement of automated digit classification systems and improving the accuracy of image-based classification tasks.

We investigate the origin of the significantly different error rates between handwritten digit machine recognition and vowel sound machine recognition. While the error rate for five Korean vowel sounds, [ɑ], [ʊ], [ɪ], [ο], and [ɛ], is about 10 percent, that of handwritten digit recognition is less than 1 percent for convolutional neural networks (CNNs) with raw data. We first dilute the information of the sound by subtracting its temporal fine structure, with the assumption that sorting out extraneous sound information will improve the accuracy of vowel recognition. Simulation results show no improvement though, indicating that the recognition rate difference does not arise from unnecessary sound information. Rather, conserving subtle information with no information reduction can be helpful to improve recognition rates; however, even the model with the highest accuracy does not reach the accuracy for handwritten digit recognition we desired. Finally, we find that the main difficulty of Korean vowel sound recognition comes from the similarity of [ο] and [ɛ]; without [ɛ], recognition of the remaining vowels is up to 99 percent. The similarity can be seen through their formant structure. Humans overcome the similarity to adeptly differentiate the two, and human vowel recognition remains far superior to the best performing CNNs. This indicates room to develop deep neural networks beyond the CNN still exists.

Handwritten digit recognition is a well-researched area in the field of pattern recognition that is used for distinguishing the pre-segmented handwritten digits. Deep learning is a recent research trend in this field and architectures like convolutional neural network (CNN) are being used. CNN is a computationally expensive architecture that is normally used to provide high accuracy in complex classification problems which require tuning of millions of parameters. On the contrary, less complex classification problems can be solved using considerably less number of parameters—hence using CNN on them leads to unnecessary wastage of resources. In the present work, we have proposed to reduce the feature maps that are used to train the CNN to reduce storage space and computation time. Experimental results show that the time required to train the CNN decreases with reducing the number of feature maps without notably affecting the accuracy.

Aim/Purpose: Our study is focused on prototyping, development, testing, and deployment of a new knowledge primitive for the humanoid robot assistant NAO, in order to enhance student visual learning by establishing a human-robot interaction. Background: This new primitive, utilizing a convolutional neural network (CNN), enables real-time recognition of handwritten digits captured by the NAO robot, a humanoid robot assistant developed by SoftBank Robotics. It is equipped with advanced capabilities, including a wide range of sensors, cameras, and interactive features. By integrating the proposed primitive, the NAO robot gains the ability to accurately recognize handwritten digits, contributing to improved student visual learning experiences. Methodology: Our developed primitive consists of the use of a convolutional neural network (CNN) so that the robot is able to recognize the handwriting of the digits present in the input image received in real-time. The NAO robot establishes interaction with the learners through a scenario based on a predefined assignment. In this scenario, NAO captures the digit handwritten by the learner via its camera, recognizes the digit using the deep learning model generated by the MNIST dataset, and announces to the learner the handwritten digit in the input image. The prototype is realized using the concept of a distributed system allowing the distribution of tasks in four different computing nodes. Contribution: Our research makes a significant contribution by equipping the humanoid robot NAO with a cognitive intelligence system through the integration of a new knowledge primitive based on handwriting digit recognition (HWDR). Our approach used to create and implement this primitive in the NAO robot is interesting and innovative, and presents a promising provision for enhancing the visual learning experience of children and young students with special needs, based on the use of distributed systems that divide the work using various components distributed over several nodes, coordinating their efforts to perform tasks more efficiently than a single device besides the NAO robot. Findings: We designed our model using specific parameters and a fully convolutional neural network architecture, which includes three residual depthwise separable convolutions, each followed by batch normalization and ReLU activation. To evaluate the performance of our model, we tested it on the MNIST dataset, where we achieved a remarkable accuracy, F1 score, and recall of 99%. An experiment was conducted to test our implemented primitive and see the effectiveness of this invention for enhancing visual learning in children with special needs. We developed a visual learning strategy based on the creation of engaging activities mediated by the NAO robot in an educational context. The results showed that participants achieved a strong commitment to the NAO robot, appreciating its ability to recognize handwritten digits and highlighting its promising potential to enrich visual learning experiences. Participants expressed a strong preference for teaching methods integrating assistive learning technologies, demonstrating the positive impact of our humanoid assistant robot on improving learning and visual intelligence in an educational environment. Recommendations for Practitioners: Encourage creativity and innovation in the field of robotics and special needs. This can lead to new and effective solutions that improve the lives of students with special needs. Recommendation for Researchers: Test and evaluate the proposed robotics solutions to ensure they are effective and making a positive impact. Use feedback from users, educators, and parents to refine and improve your solutions. Also, ensure that the robotics solutions are accessible to students with a range of abilities. This may involve designing solutions that are adjustable or providing alternative means of access. Impact on Society: As there are several ways to educate, there are multiple forms of learning. With the help of this learning procedure and strategy, the human teacher collaborates with the robot assistance NAO to improve visual learning among students. The findings of this research can serve as an application for the implementation of various pedagogical methods that will assist in meeting the needs of the majority of learners. Future Research: Our future research will concentrate on addressing the educational needs of students with special needs, enabling them to overcome their challenges and reach academic excellence in an inclusive environment. To achieve this goal, we plan to leverage the capabilities of social robots, which have emerged as a significant contributor to the field of human-robot interaction, particularly in facilitating inclusive education. These agents have proven to be effective in providing support to students with special needs, thereby enabling them to receive the education they need to succeed.

Automated image classification is an essential task of the computer vision field. The tagging of images into a set of predefined groups is referred to as image classification. The implementation of computer vision to automate image classification would be beneficial because manual image evaluation and identification can be time-consuming, particularly when there are many images of different classes. Deep learning approaches are proven to overperform existing machine learning techniques in many fields in recent years, and computer vision is one of the most notable examples. The very deep neural network (VDCNN) is a powerful deep learning model for image classification, and this paper examines it briefly using MNIST handwritten digit dataset. This dataset is used to prove the efficacy of very deep neural networks over other deep learning models. The proposed study aims to comprehend the very deep neural network architecture used to accomplish a handwritten digit recognition task. The feasibility of the proposed model is evaluated using mean accuracy, validation accuracy, and standard deviation. The study results of the very deep neural network model are compared to a convolutional neural network and convolutional neural network with batch normalization. According to the results of the comparison study, very deep neural networks achieve high accuracy of 99.1% for a handwritten dataset. The outcome of the proposed work is used to interpret how well a very deep neural network performs when compared to the other two models of deep neural networks. This proposed architecture may be used to automate the classification of handwritten digits dataset.

Convolutional neural networks are known to outperform all other neural network models when classifying a wide variety of 2D-shapes. This type of networks supports a massively parallel extraction of low-level features in the processed images. Especially this characteristic is assumed to impact the performance of convolutional networks in character recognition tasks - and in particular when considering scaled, rotated, translated or otherwise deformed patterns. Yet training of convolutional networks is rather time-consuming due to the relatively high complexity of the entire model. To speed-up the training process, we will propose a new variant of convolutional networks - the so-called hybrid convolutional neural network (HCNN). HCNN-networks combine the original idea of LeCun's convolutional networks with the benefits of RBF-like neurons in all the layers and with the winner-takes- all mechanism applied during recall. In the tests done so far in hand-written digit recognition, HCNN proved to be capable of considerably speeding-up the training process while maintaining roughly the same performance of the trained networks like original convolutional networks.

The issue of transcribed digit acknowledgment has for some time been an open issue in the field of example order. A few examined have demonstrated that Neural Network has an incredible execution in information arrangement. The fundamental target of this paper is to give effective and solid procedures to acknowledgment of transcribed numerical by looking at different existing arrangement models. This paper thinks about the exhibition of Convolutional Neural Network (CCN). Results demonstrate that CNN classifier beat over Neural Network with critical improved computational effectiveness without relinquishing execution. Handwritten digit recognition can be performed using the Convolutional neural network from Machine Learning. Using the MNIST (Modified National Institute of Standards and Technologies) database and compiling with the CNN gives the basic structure of my project development. So, basically to perform the model we need some libraries such as NumPy, `Pandas', TensorFlow, Keras. These are the main structure on which my main project stands. MNIST data contains about 70,000 images of handwritten digits from 0-9. So, it is a class 10 classification model. This dataset is divided into 2 parts i.e. Training and Test dataset. Image representation as 28*28 matrix where each cell contains grayscale pixel value.

Handwritten digit recognition is an important problem in the field of machine learning and computer vision, which is used in many practical applications such as document digitization, banking systems, postal automation, and academic assessment. Automatic identification of handwritten digits becomes a challenging task due to their variety in writing style, shape and thickness. The paper designed, implemented and evaluated a deep learning model based on the Convolutional Neural Network (CNN) using TensorFlow and Keras to accurately classify handwritten scores.The study used the MNIST dataset, which includes 60,000 training samples and 10,000 test samples in the form of grayscale images of 28 × 28 size. Under data pre-processing, techniques like normalization, re-reasoning and label encoding were adopted. The proposed CNN model incorporated convolution layers, max-pooling layers, fully-connected layers, and Softmax output layers, which enabled effective acquisition of spatial characteristics of handwritten digits.It was evident from the experimental results that the model achieved high classification accuracy, the difference between training and validation accuracy was minimal and the reliability of the classification was confirmed by confusion matrix analysis. The findings of the study indicate that the CNN-based deep learning model provides an accurate, reliable and practical solution for identifying handwritten marks.

Recently, deep learning has presented a new field of investigation for researchers in machine learning and has made it more artificial intelligence. Many domains of application are concerned by deep learning, such as health, education, robotics, surveillance, sports, etc., and more precisely Convolutional Neural Network (CNN). In fact, the CNN has become a standard to be used broadly in text classification, speech recognition, face detection, object detection, document analysis, and manuscript digit recognition. In this paper, we presented a case study consisting to recognize handwritten digits from academic transcripts. A new six-layered convolutional neural network is developed, trained using the known MNIST dataset, allowing to attain a training accuracy of 98,45% and a validation accuracy of 98,01%. Its efficiency is evaluated based on two experimental scenarios.

Artificial Neural network as a power tool is now working in more and more areas such as recognition of handwritten digits and faces, sentence classification and audio recognition. This project aims at using convolutional neural network (CNN) to recognize handwritten digits provided by MNIST datasets with TensorFlow tool. Several variables such as dropout rate, epoch, fully connected layer with different neuron amount and filter amount were investigated in the experiments to investigate the performance of the model. Both training and validation accuracy were detected and gave us a direct reflection of the influence of different settings. With appropriate 0.2 dropout rate and 50 epochs, the model can accomplish 99.81% training accuracy and 99.38% validation accuracy. By adding fully connected layers with reasonable neuron amount, both training and validation accuracy were improved, and this modification had no extra running time required in our work. The filter number in the convolutional layers was also an important factor in the model performance. More filters can extract more features from the raw images and thus increase the accuracy of 99.95% for training accuracy and 99.47% for validation accuracy. However, this modification was found to have a longer running time.

In view of the increasing demand for handwritten digit recognition, a handwritten digit recognition model based on convolutional neural network is proposed. The model includes 1 input layer and 2 convolutional layers (5*5 convolution Core), 2 pooling layers (2*2 pooling core), 1 fully connected layer, 1 output layer, and use the mnist data set for model training and prediction. After a lot of training and participation, the accuracy rate of the training set was finally reached to 100%, and the accuracy rate of 99.25% was also achieved on the test set, which can meet the requirements of recognizing handwritten digits.