Object recognition for blind people using portable camera

Mohane, Vikky; Gode, Chetan

doi:10.1109/startup.2016.7583932

Cited by 19 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [14] Scan.it is a web application applied to beat the language barriers among states and code is enforced victimization Node.js however, the inconvenience is that temperament is detected for expanse and thus equivalent letters are detected otherwise this paper presents future work for cloud deployment. In [16] used here are K-Means agglomeration for background separation and SIFT technique to want out key points of the merchandise but, the matter is it acknowledges solely encompassing objects but not the characters.…”

Section: Literature Surveymentioning

confidence: 99%

OCR Oriented Reading System for Blind People

R¹,

Revathi²

2022

AJCT

View full text Add to dashboard Cite

The current engendering of the digital phones has prominent hardware endowment and a speedier operation that is robust and ample to evolve applications that facilitate the user to be a part of and act with the Universe at their own convenience. this method is an OCR scanning system that uses a camera application present in your smartphone consolidated with Optical Character Recognition (OCR). OCR may well be a mechanism that converts pictures of manuscripts or printed content into machine-encoded text. During this system, the application will scan and convert the content that is written in English (West Germanic language) accent into a speech format. By victimization of the Text to Speech Module speech output is generated. The seek of coming up with the type of voice/speech is to give out datum that is bestowed in the given image to the visually impaired people.

show abstract

Section: Literature Surveymentioning

confidence: 99%

OCR Oriented Reading System for Blind People

R¹,

Revathi²

2022

AJCT

View full text Add to dashboard Cite

show abstract

“…However, these solutions were constrained to the limitations of smartphones, such as reduced accuracy in complex environments [11]. Another approach explored using a portable camera for object recognition and navigation assistance, offering hands-free operation and tactile feedback [12]. Yet, the potential impact of camera angles and lighting on accuracy were notable drawbacks [12].…”

Section: Introductionmentioning

confidence: 99%

“…Another approach explored using a portable camera for object recognition and navigation assistance, offering hands-free operation and tactile feedback [12]. Yet, the potential impact of camera angles and lighting on accuracy were notable drawbacks [12]. A recent study aimed at Arabic-speaking users also implemented a deep learning approach for object recognition and audio feedback [13].…”

Section: Introductionmentioning

confidence: 99%

Robotic Assistant for Object Recognition Using Convolutional Neural Network

Oluyele,

Adeyanju,

Sobowale

2024

AJERD

View full text Add to dashboard Cite

Visually impaired persons encounter certain challenges, which include access to information, environmental navigation, and obstacle detection. Navigating daily life becomes a big task with challenges relating to the search for misplaced personal items and being aware of objects in their environment to avoid collision. This necessitates the need for automated solutions to facilitate object recognition. While traditional methods like guide dogs, white canes, and Braille have offered valuable solutions, recent technological solutions, including smartphone-based recognition systems and portable cameras, have encountered limitations such as constraints relating to cultural-specific, device-specific, and lack of system autonomy. This study addressed and provided solutions to the limitations offered by recent solutions by introducing a Convolutional Neural Network (CNN) object recognition system integrated into a mobile robot designed to function as a robotic assistant for visually impaired persons. The robotic assistant is capable of moving around in a confined environment. It incorporates a Raspberry Pi with a camera programmed to recognize three objects: mobile phones, mice, and chairs. A Convolutional Neural Network model was trained for object recognition, with 30% of the images used for testing. The training was conducted using the Yolov3 model in Google Colab. Qualitative evaluation of the recognition system yielded a precision of 79%, recall of 96%, and accuracy of 80% for the Robotic Assistant. It also includes a Graphical User Interface where users can easily control the movement and speed of the robotic assistant. The developed robotic assistant significantly enhances autonomy and object recognition, promising substantial benefits in the daily navigation of visually impaired individuals.

show abstract