Recognition and Translation of Thai Characters and Words from Text

-
Recognition and Translation of Thai Characters and Words from Text

OUTPUT


Goal/Objective:

● Detect, segment, and translate Thai characters from images of printed text. (Character classification)
○ This includes characters that have been rotated, slanted, within noisy images,
and in uneven lighting conditions.
○ Initially, we will test and work on detecting a single font of Thai, then add different
fonts and sizes to improve algorithm robustness.
○ We will also just start with the 44 consonants and if we are able to characterize
these, we will move on to the different vowels that exists on top, underneath, and
on the side of consonants.
● We will collect data​ from Thai newspaper websites.
○ First our training data on one font would be done by copying text into google docs
and printing them out as a jpeg images.
○ We will physically print them out and take photos of these document in different
lightings and orientations. Use these as both training and test data.
○ We will then use images from actual newspapers that’s been downloaded online
as further test data with different fonts and sizes.
● Translate the text after language detection
● Reach Goal: Machine learning to derive feature model for vowel and consonant
detection, primary handwritten Thai.
● We will evaluate ​our performances on the percentage of correct character classifications
of each characters. The number of false positives and misclassifications. We will try to
increase the correct characterization percentage and decrease misclassification and
false positive percentages.

Methods:

1. Create database of Thai characters starting with one font then using multiple fonts.
a. Obtain computer type font screenshots of the 44 Thai consonants, its 15 vowel
symbols, and the various vowel forms to use as character templates.
2. Generate character detection filters, such as hit-miss and minimum rank filters, and
templates from various Thai fonts.
3. Process and extract features and characters from images via locally adaptive gray level
thresholding, binarization, and region moments.
a. Resize and rotate images for proper matching and alignment
b. Reduce noise with median filtering, etc.
c. Identify regions of neighboring text.
4. Detect characters using filters and template matching.
5. Translate words and sentences with Google
6. Additional: extract features of different Thai consonants and vowels using machine
learning tools to create a model to detect handwritten Thai.

FOR BASE PAPER PLEASE MAIL US

DOWNLOAD 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 da...
Read more

Face Detection, Extraction, and Swapping on Mobile Devices

-
Image
Face Detection, Extraction, and Swapping on Mobile Devices OUTPUT: DOCUMENTATION: We will use the Viola-Jones face detector in OpenCV as a starting point. Once we have found two faces we will apply some post processing to make sure that we have the entire face without any holes. Once we have a binary mask of the faces’ fully connected components, we plan to use cvBlobsLib (similar to regionprops function in Matlab) to do face region labelling and extraction. Choosing the faces to swap will either be random or done through a simple UI. Initially we will translate the faces to match the new face’s centroid with the centroid of the old face. Then, using the relative locations of features detected using OpenCV (such as the eyes, nose, and mouth) we will determine the orientation of the face in the plane parallel to the camera lens. Then, the relative sizes of these features will allow us to determine the degree of rotation away from the camera. However, if the faces we ar...
Read more