This study explores the challenges faced by visually impaired individuals using screen readers in the workplace and proposes the development of assistive tools to address these challenges. Interviews with five visually impaired workers revealed difficulties related to screen reader compatibility, image and character recognition, and lack of accessibility awareness. The data, analyzed by clustering, highlighted significant issues such as inaccessibility of PDFs, icons without alternative text, and inadequate visual layouts. The research emphasizes the need for improved tools to bridge the information access gap, demonstrating the potential of AI and image recognition technologies in creating more inclusive work environments. Future work will focus on developing a tool that interprets icons' functions and presents them in a screen-reader-friendly format.

In this paper, we propose a system for recognizing an expiration date of perishable food products. A visually impaired user takes a photo of the product. Then, the system automatically recognizes the expiration date of the product and tells it to the user. The dates in the image were sometimes skewed, misaligned, or partially missing. To solve these problems, we use Spatial Transformer Network (STN) to recognize skewed, misaligned, or partially missing date images. STN explicitly allows the spatial manipulation of data within the neural network.

We propose a dedicated CNN with STN expiration date recognition. The input to this network is an image of the expiration date. The network has six STNs to detect each digit of the date. Each STN outputs the rectified image of the digits. The image of the digits is then recognized by the traditional CNN.

We trained the expiration date recognition network. The network converged quickly, and the training was stopped in 10 epochs. We tested this network on 1088 date images that were not used during training. The experimental results showed that the system was able to achieve a high recognition rate of 99.42% for the dataset without dates with spaces and 98.44% for the dataset with dates with spaces.

The objective of this research is to explore ICT trends and their potential impact on EOM prosthesis implant surgeries, with a specific emphasis on improving accessibility and surgical outcomes.

Research Questions:

1. What imaging modalities and data sources are essential for constructing Digital Twins tailored for Strabismus Surgeries?
2. What medical image databases exist for addressing EOM issues, particularly in the context of Strabismus?
3. What are the current diagnostic image processing and neural network algorithms available for detecting Strabismus?
4. What components constitute the 3D geometrical models utilized in EOM simulators?
5. How can the eye be quantified using medical imaging?
6. What frameworks and algorithms are available for converting medical imaging into three-dimensional geometrical models, facilitating diagnosis and simulation?
7. What mathematical models are employed in EOM simulations to enhance understanding and training?

Methods: The SLR methodology was employed, incorporating diverse research questions and precise definitions. A total of 14 essential keywords were identified, leading to the selection of six appropriate databases. Following rigorous search criteria, 56 relevant research papers were identified and analyzed.

Results: Existing databases primarily rely on digital imaging, lacking explicit medical image repositories. Various AI and ML algorithms were identified for diagnosing Strabismus, though a scarcity of algorithms based on medical images was observed.