School of Science and Technology 科技學院
Computing Programmes 電腦學系
| Programme | Bachelor of Computing with Honours in Internet Technology |
| Supervisor | Dr. Vanessa Ng |
| Areas | Intelligent Applications |
| Year of Completion | 2018 |
The aim of this project is to develop an application to assist visually impaired in shopping products in supermarket. As there are numerous products in a supermarket, we will focus on the canned food in this project. The reason is that canned foods have the similar shape which makes visually impaired cannot distinguish among them by touching. If they have an allergy to some food such as pork or beef, the consequence of misidentification may be fatal.
For this application, object recognition based on machine learning will be used to classify different canned foods. Object recognition is recognizing the canned foods from an image. Machine learning approach allows the application to learn from numerous data and perform recognition after training.
To achieve the aim, the main objective of the project is to recognize different canned foods through smartphone's camera. The project has also defined several sub-objectives as follows:
To assist visually impaired in shopping products, the solution should be portable and provide relevant information to them. A mobile platform prototype solution to assist visually impaired in shopping products based on machine learning is designed in this project.
The prototype solution is developed to classify canned foods. Visually impaired can access through simple gestures, the application can recognize the canned food in photos which taken by them. The latest information of the canned foods will be read out to them.
Agile Development is used through the development of this project. Features such as Optical Character Recognition and guiding module are added to the application one by one with the integrated test.
Figure 1: Information flow diagram
Figure 2: Chopped pork and ham: Highlights of text information
The text on canned foods is useful in classifying the canned food. To extract the printed text, we need Optical Character Recognition. As it is difficult to build our own OCR, we used the OCR service provided by Google. Google Vision provides OCR service, we can use the service through sending HTTP requests.
Once the photos are sent to Google Vision, it returns a JSON object which is including the recognized text in the photos. Our server will extract the text in JSON object and compare to the words stored in the Database. We will rate the canned foods according to the matched word and their weighting. The score will be normalized and sum with the result from the machine learning model for predicting the canned food.
Although the text canned food is informative, there are some limitations of OCR. Since the photos taken by visually impaired may not be clear enough to recognize, we cannot rely on the result of OCR only. Also, the text on canned food is not always in proper font. As in figure 13, the Chinese words ”火腿豬肉” cannot be recognized by OCR. So, the machine learning model is essential in recognizing the canned foods.
After performed several evaluations to the prototype, our team found that iDetect can assist visually impaired in shopping products without help from others and gain more independence in their daily life. This makes them to have a stronger intention to go outside and join the majority.
However, our solution is not perfect. There are some limitations in our solution.
Firstly, the provided information is not enough. For this prototype, what iDetect provides are only the price, brand, name, volume and special offer of the canned food. However, these may not enough for visually impaired to enjoy shopping in supermarkets. For example, our group, as ordinary people, we always want to read nutrition facts printed on the package to protect our health. Visually impaired do have this demand too. But it is quite difficult for our team to collect nutrition facts for each product from a reliable source. If the solution can provide the nutrition facts, visually impaired can shop in supermarkets with more supports.
Secondly, the solution is not able to provide an offline service. Since the relevant information of canned food is updated hourly, which is a power and bandwidth consuming operation, it is not suitable to store canned food information into the user's phone. However, according to our team's experience, phones may have bad reception in some supermarkets, especially in some underground supermarkets. iDetect may be out of service in these situations. If iDetect can be used offline, users are able to use it everywhere.
For the future work, iDetect can be enhanced by increasing the number of supported products. Canned food is only one kind of products in supermarkets. There are more kinds of products in supermarkets, such as drinks, snack foods, wines, etc. Visually impaired can have more choices when they are shopping in supermarkets.
Furthermore, iDetect can also be enhanced by providing iOS version. Not all the visually impaired use Android phone. Some of them may use iPhone. Providing IOS version can benefit more visually impaired.
Jonathan handles all external affairs include business development, patents write up and public relations. He is frequently interviewed by media and is considered a pioneer in 3D printing products.
After graduating from OUHK, Krutz obtained an M.Sc. in Engineering Management from CityU. He is now completing his second master degree, M.Sc. in Biomedical Engineering, at CUHK. Krutz has a wide range of working experience. He has been with Siemens, VTech, and PCCW.
Hugo Leung Wai-yin, who graduated from his four-year programme in 2015, won the Best Paper Award for his ‘intelligent pill-dispenser’ design at the Institute of Electrical and Electronics Engineering’s International Conference on Consumer Electronics – China 2015.
The pill-dispenser alerts patients via sound and LED flashes to pre-set dosage and time intervals. Unlike units currently on the market, Hugo’s design connects to any mobile phone globally. In explaining how it works, he said: ‘There are three layers in the portable pillbox. The lowest level is a controller with various devices which can be connected to mobile phones in remote locations. Patients are alerted by a sound alarm and flashes. Should they fail to follow their prescribed regime, data can be sent via SMS to relatives and friends for follow up.’ The pill-dispenser has four medicine slots, plus a back-up with a LED alert, topped by a 500ml water bottle. It took Hugo three months of research and coding to complete his design, but he feels it was worth all his time and effort.
Hugo’s public examination results were disappointing and he was at a loss about his future before enrolling at the OUHK, which he now realizes was a major turning point in his life. He is grateful for the OUHK’s learning environment, its industry links and the positive guidance and encouragement from his teachers. The University is now exploring the commercial potential of his design with a pharmaceutical company. He hopes that this will benefit the elderly and chronically ill, as well as the society at large.
Soon after completing his studies, Hugo joined an automation technology company as an assistant engineer. He is responsible for the design and development of automation devices. The target is to minimize human labor and increase the quality of products. He is developing products which are used in various sections, including healthcare, manufacturing and consumer electronics.
| Course Code | Title | Credits | |
|---|---|---|---|
| COMP S321F | Advanced Database and Data Warehousing | 5 | |
| COMP S333F | Advanced Programming and AI Algorithms | 5 | |
| COMP S351F | Software Project Management | 5 | |
| COMP S362F | Concurrent and Network Programming | 5 | |
| COMP S363F | Distributed Systems and Parallel Computing | 5 | |
| COMP S382F | Data Mining and Analytics | 5 | |
| COMP S390F | Creative Programming for Games | 5 | |
| COMP S492F | Machine Learning | 5 | |
| ELEC S305F | Computer Networking | 5 | |
| ELEC S348F | IOT Security | 5 | |
| ELEC S371F | Digital Forensics | 5 | |
| ELEC S431F | Blockchain Technologies | 5 | |
| ELEC S425F | Computer and Network Security | 5 |
| Course Code | Title | Credits | |
|---|---|---|---|
| ELEC S201F | Basic Electronics | 5 | |
| IT S290F | Human Computer Interaction & User Experience Design | 5 | |
| STAT S251F | Statistical Data Analysis | 5 |
| Course Code | Title | Credits | |
|---|---|---|---|
| COMPS333F | Advanced Programming and AI Algorithms | 5 | |
| COMPS362F | Concurrent and Network Programming | 5 | |
| COMPS363F | Distributed Systems and Parallel Computing | 5 | |
| COMPS380F | Web Applications: Design and Development | 5 | |
| COMPS381F | Server-side Technologies and Cloud Computing | 5 | |
| COMPS382F | Data Mining and Analytics | 5 | |
| COMPS390F | Creative Programming for Games | 5 | |
| COMPS413F | Application Design and Development for Mobile Devices | 5 | |
| COMPS492F | Machine Learning | 5 | |
| ELECS305F | Computer Networking | 5 | |
| ELECS363F | Advanced Computer Design | 5 | |
| ELECS425F | Computer and Network Security | 5 |
