• Version
• Download 122
• File Size 532.08 KB
• File Count 1
• Create Date 23 June 2023
• Last Updated 23 June 2023

Smart Image To Text And Text To Speech Recognition Using Machine Learning

Dr.S.C.Wagaj, Mrs.Lata More, Harshada Kamble, Nikita Pakhale

Electronics & Telecommunication
JSPM’S Rajarshi Shahu College of Engineering
Pune, India

Abstract—The optical character recognition (OCR) and text-to-speech (TTS) concepts are combined in this project. By successfully establishing a voice interface connection with computers, this type of framework helps persons who are visually handicapped. Image to text and text to speech conversion is a technique that uses the OCR method to read and scan 20+ different languages and numbers in the image and converts them to voices. The voice processing module and the picture processing module are both implemented in this project. Numerous methods have been used in the past, such as the Edged Based Method, Connected Component Method, Texture-Based Method, and Mathematical Morphology Method, however they have significant limitations when measured by exactness, f-score, and review. These picture texts can be found in magazines, photographs, newspapers, banners, and other media. The development of intelligent systems to enhance quality of life is the focus of current technological developments in the fields of natural language processing and image processing. An efficient method for text recognition, extraction from images, and text-to-speech conversion is proposed in this paper. In this work, a successful method for text detection, extraction from photos, and text to speech conversion is suggested. The incoming image is first improved by using grey scale conversion. Then, using the maximum stable external areas feature detector, the text portions of the improved image are located. The following step is to use geometric filtering along with a stroke width transform to effectively gather and filter text sections in a picture. The geometric properties and stroke width transform are used to remove the non-text maximum stable exterior regions. Individual letters and alphabets are then grouped to find text sequences, which are subsequently broken up into words. In order to digitize the words, optical character recognition (OCR) is used. The text is converted to speech in the final phase by feeding it through our text-to-speech synthesizer (TTS). On images from documents to nature settings, the suggested method is tested. The correctness and robustness of the suggested framework have been demonstrated by promising findings, which promote its practical use in real-world applications.

Keywords— Image Processing, Text Recognition and Extraction, Maximally stable extremal regions, OCR(Optical Character-Recognition),SWT(Stroke-Width-Transform) TTS(Text-to-speech synthesizer)