No description available.

No description available.

By organically fusing the methods of convolutional neural network (CNN) and recurrent neural network (RNN), this dissertation focuses on the application of optical character recognition and image classification processing. The first part of this dissertation presents an end-to-end novel receipt recognition system for capturing effective information from receipts (CEIR). The main contributions of this research part are divided into three parts. First, this research develops a preprocessing method for receipt images. Second, the modified connectionist text proposal network is introduced to execute text detection. Third, the CEIR combines the convolutional recurrent neural network with the connectionist temporal classification with maximum entropy regularization as a loss function to update the weights in networks and extract the characters from receipt. The CEIR system is validated with the scanned receipts optical character recognition and information extraction (SROIE) database. Furthermore, the CEIR system has strong robustness and can be extended to a variety of different scenarios beyond receipts. For the convolutional recurrent structure application of land use image classification, this dissertation comes up with a novel deep learning model for land use classification, the convolutional recurrent land use classifier (CRLUC), which further improves the accuracy in classifying remote sensing land use images. Besides, the convolutional fully-connected neural networks with hard sample memory pool structure (CFMP) is invented to tackle the remote sensing land use image classification tasks. The CRLUC and CFMP algorithm performances are tested in popular datasets. Experimental studies show the proposed algorithms can classify images with higher accuracy and fewer training episodes compared to popular image classification algorithms.

This thesis is a benchmark performed on three commercial Optical Character Recognition (OCR) engines. The purpose of this benchmark is to characterize the performance of the OCR engines with emphasis on the correlation of errors between each engine. The benchmarks are performed for the evaluation of the effect of a multi-OCR system employing a voting scheme to increase overall recognition accuracy. This is desirable since currently OCR systems are still unable to recognize characters with 100% accuracy. The existing error rates of OCR engines pose a major problem for applications where a single error can possibly effect significant outcomes, such as in legal applications. The results obtained from this benchmark are the primary determining factor in the decision of implementing a voting scheme. The experiment performed displayed a very high accuracy rate for each of these commercial OCR engines. The average accuracy rate found for each engine was near 99.5% based on a less than 6,000 word document. While these error rates are very low, the goal is 100% accuracy in legal applications. Based on the work in this thesis, it has been determined that a simple voting scheme will help to improve the accuracy rate.

The CAR (confront, address, replace) Strategy is an antiracist pedagogy aiming to drive out exclusionary terminology in engineering education. “Master-slave” terminology is still commonplace in engineering education and industry. However, questions have been raised about the negative impacts of such language. Usage of exclusionary terminology such as “master-slave” in academia can make students—especially those who identify as women and/or Black/African-American—feel uncomfortable, potentially evoking Stereotype Threat (Danowitz, 2020) and/or Curriculum Trauma (Buul, 2020). Indeed, prior research shows that students from a number of backgrounds find non-inclusive terminologies such as “master-slave” to be a major problem (Danowitz, 2020). Currently, women-identifying and gender nonbinary students are underrepresented in the engineering industry (ASEE, 2020) while Black/African-American students are underrepresented in the entire higher education system, including engineering fields (NSF, 2019). The CAR Strategy, introduced here, stands for: 1) confront; 2) address; 3) replace and aims to provide a framework for driving out iniquitous terminologies in engineering education such as “master-slave.” The first step is to confront the historical significance of the terminology in question. The second step is to address the technical inaccuracies of the legacy terminology. Lastly, replace the problematic terminology with an optional but recommended replacement. This thesis reports on student perceptions and the effectiveness of The CAR Strategy piloted as a teaching framework in the computer engineering department of Cal Poly. Of 64 students surveyed: 70% either agree or strongly agree that The CAR Strategy is an effective framework for driving out exclusionary terminologies. Amman Asfaw first presented certain portions of this thesis at the virtual 2021 American Society for Engineering Education (ASEE) Annual Conference and Exposition. The original publication’s copyright is held by ASEE (Asfaw, 2021); secondary authors included Storm Randolph, Victoria Siaumau, Yumi Aguilar, Emily Flores, Dr. Jane Lehr, and Dr. Andrew Danowitz.

This study is dedicated to enhancing the effectiveness of Optical Character Recognition (OCR) systems, with a special emphasis on Arabic handwritten digit recognition. The choice to focus on Arabic handwritten digits is twofold: first, there has been relatively less research conducted in this area compared to its English counterparts; second, the recognition of Arabic handwritten digits presents more challenges due to the inherent similarities between different Arabic digits.OCR systems, engineered to decipher both printed and handwritten text, often face difficulties in accurately identifying low-quality or distorted handwritten text. The quality of the input image and the complexity of the text significantly influence their performance. However, data augmentation strategies can notably improve these systems' performance. These strategies generate new images that closely resemble the original ones, albeit with minor variations, thereby enriching the model's learning and enhancing its adaptability. The research found Conditional Variational Autoencoders (C-VAE) and Conditional Generative Adversarial Networks (C-GAN) to be particularly effective in this context. These two generative models stand out due to their superior image generation and feature extraction capabilities. A significant contribution of the study has been the formulation of the Synthetic Image Evaluation Procedure, a systematic approach designed to evaluate and amplify the generative models' image generation abilities. This procedure facilitates the extraction of meaningful features, computation of the Fréchet Inception Distance (LFID) score, and supports hyper-parameter optimization and model modifications.

Various document layout analysis techniques are employed in order to enhance the accuracy of optical character recognition (OCR) in document images. Type-specific document layout analysis involves localizing and segmenting specific zones in an image so that they may be recognized by specialized OCR modules. Zones of interest include titles, headers/footers, paragraphs, images, mathematical expressions, chemical equations, musical notations, tables, circuit diagrams, among others. False positive/negative detections, oversegmentations, and undersegmentations made during the detection and segmentation stage will confuse a specialized OCR system and thus may result in garbled, incoherent output. In this work a mathematical expression detection and segmentation (MEDS) module is implemented and then thoroughly evaluated. The module is fully integrated with the open source OCR software, Tesseract, and is designed to function as a component of it. Evaluation is carried out on freely available public domain images so that future and existing techniques may be objectively compared. / Master of Science

Tez (Yüksek Lisans) - Süleyman Demirel Üniversitesi, Fen Bilimleri Enstitüsü, Elektronik ve Haberleşme Mühendisliği Anabilim Dalı, 2007. / Kaynakça var.

This thesis deals with the evaluation forms using optical character recognition. Image processing and methods used for OCR is described in the first part of thesis. In the practical part is created database of sample characters. The chosen method is based on correlation between patterns and recognized characters. The program is designed in a graphical environment MATLAB. Finally, several forms are evaluated and success rate of the proposed program is detected.

As an effort to improve accessibility to historical documents, digitization of historical archives has been an ongoing process at many institutions since the origination of Optical Character Recognition. The old, scanned documents can contain deteriorations acquired over time or caused by old printing methods. Common visual attributes seen on the documents are variations in style and font, broken characters, ink intensity, noise levels and damage caused by folding or ripping and more. Many of these attributes are disfavoring for modern Optical Character Recognition tools and can lead to failed character recognition. This study approaches stated problem by using image processing methods to improve the result of character recognition. Furthermore, common image quality characteristics of scanned historical documents with unidentifiable text are analyzed. The Optical Character Recognition tool used to conduct this research was the open-source Tesseract software. Image processing methods like Gaussian lowpass filtering, Otsu’s optimum thresholding method and morphological operations were used to prepare the historical documents for Tesseract. Using the Precision and Recall classification method, the OCR output was evaluated, and it was seen that the recall improved by 63 percentage points and the precision by 18 percentage points. This shows that using image pre-processing methods as an approach to increase the readability of historical documents for Optical Character Recognition tools is effective. Further it was seen that common characteristics that are especially disadvantageous for Tesseract are font deviations, occurrence of non-belonging objects, character fading, broken characters, and Poisson noise.