Signboard Character Recognition

-
✔️Signboard Character Recognition


✔️Motivation

Imagine a world in which a person can walk down any street and take a picture of a random
store’s signboard with a mobile device, enabling him or her to know what goods or service the store provides, the ratings of the store, his or her geolocation, and even suggestions on nearby shops that may interest him or her.

✔️Goal

We will specifically tackle the problem of the signboard character recognition. Although OCR has been around for a while and is now commonly used to convert scanned documents [3] and license plate [1] to text, the problem we are tackling here is more interesting. Specifically, the signboard can be of different color, the signboard text can be non-standard, the signboard image can be taken at an angle, and the exterior of the signboard has to be removed when performing OCR.

✔️Our Initial Thought on Implementation
1. Input of the original (RGB) image.
2. Convert the image to grayscale.
3. Remove all background and the noise. (Not sure how to implement this yet)
4. Image binarization with Otsu’s method, taking the background to be either white or black depending on which color is more dominant in the image.
5. Perform homography and Hough transform to correct the angle and alignment of the signboard.
6. Use a traditional OCR technique to parse out the signboard characters.

✔️Challenges

After being affirmed by the TA that this project proposal is not impossible, we would still like to have a mentor who can help us on these task. Specifically, we do not know where to start tackling Step 5  (angle correction) and Step 6 (traditional OCR technique).
Android Statement We do not plan to implement on Android. Although the ultimate goal is to have this processing done on a mobile device, for this project, we only consider building the computation backend.


✔️References

[1] Wanniarachchi, W.; Sonnadara, D.U.J.; Jayananda, M.K., "License plate identification based on image processing techniques," in Industrial and Information Systems, 2007. ICIIS 2007. International Conference on , vol., no., pp.373-378, 9-11 Aug. 2007
doi: 10.1109/ICIINFS.2007.4579205
[2] Oosterman, J.; Green, R., "Geolocation on the iPhone by automatic street sign reading," in Image and Vision Computing New Zealand (IVCNZ), 2010 25th International Conference of , vol., no., pp.1-6, 8-9 Nov. 2010
[3] Sharma, N.; Kumar, B.; Singh, V., "Recognition of off-line hand printed English Characters, Numerals and Special Symbols," in Confluence The Next Generation Information Technology Summit (Confluence), 2014 5th International Conference - , vol., no., pp.640-645, 25-26 Sept. 2014
[4] Cambra, A.B.; Murillo, A.C., "Towards robust and efficient text sign reading from a mobile phone,"in Computer Vision Workshops (ICCV Workshops), 2011 IEEE International Conference on , vol., no., pp.64-71, 6-13 Nov. 2011
[5] Mullah et al. “Design of an Optical Character Recognition System for Camera- based Handheld Devices”, in IJCSI International Journal of Computer Science Issues, Vol. 8, Issue 4, No 1, July 2011

PROJECT SOURCE CODE CLICK HERE

Comments

Post a Comment

Popular posts from this blog

Light Field Images for Background Removal

-
Image
Light Field Images for Background Removal OUTPUT OVERVIEW Standard edge detection or foreground/background separation techniques, such as Otzu’smethod, require color or intensity differences between the background and regions that need tobe separated. For example, green screens are routinely set up as the background in a scene so thatthere is a clear difference in color between the background and foreground.Light filed images, captured in 4D and passively containing depth information for thescene can be used to approximate this effect. Depth estimation in the scene alone could provide a metric to separate the foreground and background, but more sophisticated methods are available.Considering the edge detection from a single image from a single viewpoint and analyzing the depths from the light field around the edges in that image, occluded edges and intensity or color edges can be distinguished. Along with the rest of the depth information this can allow the foreground and b
Read more

Using Image Processing to Identify and Score Darts thrown into a Dartboard

-
Image
✔️Using Image Processing to Identify and Score Darts thrown into a Dartboard ✔️Introduction The game of darts is a throwing sport in which participants toss projectiles into a circular target  attached to a vertical surface. The target is divided into many regions which correspond to different point and multiplier values. Darts is commonly played across North America and Europe and is a popular past time for many so an application that allows players to more conveniently keep score would be widely  beneficial. “Darts” is a general term for a targeting game following this basic premise and many game variations exist within this archetype; all utilizing the standard dart projectiles with a regulation dart board. Each game variant may have different objectives for which players to aim but identifying the region in  which the dart has hit in the dartboard is necessary for proper scoring. This project proposes the use of image processing to identify thrown darts and to det
Read more

Digital Make up Face Generation

-
Image
Digital Make up Face Generation Goal Current make-up applications rely on using photoshop tools to apply makeup on the target's digital  faces and generate results. While these applications allow customization, a customer who wants to  quickly decide on the type of makeup kit to buy at a store will not find it useful. The customer might just  want to find out how the make-up look on the cover or billboard will look like on her face. The goal of  this project is to use an existing reference image of another subject with a make-up applied, and  transfer the reference's make up on the target's face. The application can be further extended to photo  retouching and illumination transfer from the reference image to the target. Methodology In order to transfer the make-up from the reference onto target in a pixel by pixel basis, the areas of  interest must align. Face features such as eyes, nose, mouth and contours of the face, will be recognized  using Active Shape
Read more