Object finder

1798 Words4 Pages

1 Introduction
1.1 Problem Description
Nowadays, disadvantages people such as visually impaired people are around the world. According to World Health Organization (WHO) estimated in 2013, there are 285 million of world population who are visually impaired. Furthermore, 39 millions out of the population are blind. These people require assistance in their daily life such as locating and grabbing objects (i.e. a cup, a key, etc.) which may have been fallen or misplaced. This is because, they have less information about the environment. Hence, developing assistive technology and handheld devices can help them to increase the independence and inconveniences. The final goal is to improve their life with today's state-of-the-art technology.
1.2 Motivation
Visually impaired people encounter inconvenience when interacting with their surrounding environments. The most challenge is to find a specific object. This proposed system is designed in such a way to help the visually impaired people to increase the ease to navigate hand to locate and grab their necessities in an environment. Computer vision and image processing play an important role in this system. Images contain many information that can be used to aid them understand the surrounding environment well. Also, every object has its own local features such as regions, blobs and points. By using the feature points in the images, it is easier for object recognition that can help visually impaired. Therefore, using this method, visually impaired people can reduce their inconveniences and improve their life.
1.3 Proposed Approach

Figure 1 Feature points finding process.
Generally, the object detection is simplified in a way that the system will focus on pre-determined invariant SURF fe...

... middle of paper ...

...ems in daily life through a wearable web camera in order to reduce the inconveniences. Additionally, it can guide user’s hand to locate and grab their necessities in an environment.
The main focus of this system is on employing feature points for object recognition. Speed-Up Robust Feature (SURF) is rotation invariant and scale invariant. It can handle image translation, scaling, change in viewpoint and rotation between objects in the cluttered background. Thus, it is being used as feature detector and feature descriptor for this system.
6.1 Future Works
The future work will concentrate on enhancing object recognition system so that it can better identify and detect objects in different conditions. Besides that, Human Computer Interface (HCI) will be included to the system for auditory display and image capture of the object recognition on Smartphone and computer.

Open Document