Object recognition in a mobile phone application for visually impaired users

Matusiak, Karol; Skulimowski, Piotr; Strurnillo, P.

doi:10.1109/hsi.2013.6577868

Cited by 50 publications

(18 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Object recognition is a highly active topic in computer vision and can be particularly useful for mobile devices [1,2] as regards retrieving information about objects on the fly. Visually impaired persons can also benefit from these systems [3].…”

Section: Introductionmentioning

confidence: 99%

MirBot: A collaborative object recognition system for smartphones using convolutional neural networks

2018

View full text Add to dashboard Cite

MirBot is a collaborative application for smartphones that allows users to perform object recognition. This app can be used to take a photograph of an object, select the region of interest and obtain the most likely class (dog, chair, etc.) by means of similarity search using features extracted from a convolutional neural network (CNN). The answers provided by the system can be validated by the user so as to improve the results for future queries. All the images are stored together with a series of metadata, thus enabling a multimodal incremental dataset labeled with synset identifiers from the WordNet ontology. This dataset grows continuously thanks to the users' feedback, and is publicly available for research. This work details the MirBot object recognition system, analyzes the statistics gathered after more than four years of usage, describes the image classification methodology, and performs an exhaustive evaluation using handcrafted features, neural codes, different transfer learning techniques, PCA compression and metadata, which can be used to improve the image classifier results. The app is freely available at the Apple and Google Play stores.

show abstract

Section: Introductionmentioning

confidence: 99%

MirBot: A collaborative object recognition system for smartphones using convolutional neural networks

2018

View full text Add to dashboard Cite

show abstract

“…For security and verification purpose we need to detect and recognize an object and most importantly object recognition application for mobile phones in favour of persons having partial vision eye sight is a major scope for object recognition system [8], [10], [11].…”

Section: Introductionmentioning

confidence: 99%

Object recognition with plain background by using ANN and SIFT based features

Sinkar

Deshpande

2015

2015 International Conference on Information Processing (ICIP)

View full text Add to dashboard Cite

In this paper, we have developed algorithm which combine features from an object image to recognize it. Object recognition is the most interesting and challenging area of research due to its importance to a wide range of applications as objects differ in shape, size and color. The descriptors used for feature extraction in the existing methods for object recognition are mostly intensity based. For the recognition of object with varying level of light illumination color descriptors have been used in this paper. The color descriptors used in the object recognition system are based upon the intensity levels of hue (H), saturation (S) and value (V) in terms of their histogram for respective object image. The system works in single object recognition mode with plain background. The features used for recognition are mainly the size (along the boundaries) and HSV intensity values of the object's image. It consists of two key modules, feature extraction and object recognition. In this paper object recognition is accomplished by using two different methods in which the classification of the extracted features of object image are on the basis of artificial neural networks (ANN) and scale invariant feature transform (SIFT) based features. We have adapted the Euclidean distance measure metric algorithm for matching the extracted features of object's image. Finally the results in terms of object detection and recognition rates are calculated on the basis of false rejection ratio (FRR) and false acceptance ratio (FAR).

show abstract

“…One of the objectives in taking up this work is to develop mobile handset base denomination identification system for visually impaired and blind people. The available computing power and memory space in mobile handset [14,25 ] devices will be the constraining factors for such system. In this work we have compared keypoint descriptors SURF and FREAK for the images INR notes.…”

Section: Introductionmentioning

confidence: 99%

Comparative study of SURF and FREAK descriptor on Indian Rupee Currency notes

Mulmule-Shirkhedkar¹,

Dani²

2015

2015 International Conference on Information Processing (ICIP)

View full text Add to dashboard Cite

In this paper we present comparative study of two descriptors namely fast retina key point descriptor and speeded up robust features for feature extraction and feature matching of images of Indian Currency notes of different denominations. The suitability of these features for automatically identifying denominations of these notes has been studied. The speed and memory load of two different descriptors has been evaluated for suitability of developing mobile based application for identifying denominations of Indian Rupee notes. The robustness of these features is also evaluated with rotated, scaled and illumination variation in currency banknote images. II. RELATED WORKKeypoints are the points of interest (also called as interest points) in an image where the intensity changes sharply [24]. Keypoints in an image can be corners, edges and blobs. Keypoint detectors help in locating the points of interest in an image. On the other hand keypoint descriptors allow us to compare the features of different images. The development of

show abstract

Object recognition in a mobile phone application for visually impaired users

Cited by 50 publications

References 6 publications

MirBot: A collaborative object recognition system for smartphones using convolutional neural networks

MirBot: A collaborative object recognition system for smartphones using convolutional neural networks

Object recognition with plain background by using ANN and SIFT based features

Comparative study of SURF and FREAK descriptor on Indian Rupee Currency notes

Contact Info

Product

Resources

About