Chomtip Pornpanomchai

Vehicle speed detection system

This research intends to develop the vehicle speed detection system using image processing technique. Overall works are the software development of a system that requires a video scene, which consists of the following components: moving vehicle, starting reference point and ending reference point. The system is designed to detect the position of the moving vehicle in the scene and the position of the reference points and calculate the speed of each static image frame from the detected positions. The vehicle speed detection from a video frame system consists of six major components: 1) Image Acquisition, for collecting a series of single images from the video scene and storing them in the temporary storage. 2) Image Enhancement, to improve some characteristics of the single image in order to provide more accuracy and better future performance. 3) Image Segmentation, to perform the vehicle position detection using image differentiation. 4) Image Analysis, to analyze the position of the reference starting point and the reference ending point, using a threshold technique. 5) Speed Detection, to calculate the speed of each vehicle in the single image frame using the detection vehicle position and the reference point positions, and 6) Report, to convey the information to the end user as readable information. The experimentation has been made in order to assess three qualities: 1) Usability, to prove that the system can determine vehicle speed under the specific conditions laid out. 2) Performance, and 3) Effectiveness. The results show that the system works with highest performance at resolution 320×240. It takes around 70 seconds to detect a moving vehicle in a video scene.

Vehicle detection and counting from a video frame

The research intends to develop the vehicle detection and counting system using image processing. Overall works are software development of a system that requires a video stream and capture to a video frame. They consist of the following components: background road without any moving vehicle and the frame with moving vehicles. The system is designed to find the differentiation which is the moving vehicles and find the number of moving vehicles from the video frame. The vehicle detection and counting system consists of four major components: 1) image acquisition, 2) image analysis, 3) object detection and counting, and 4) Display Result The experiment has been conducted in order to access the following qualities: 1) Usability, to prove that the system can determine vehicle detection and counting under the specific condition lay out. 2) Efficiency, to show that the system can work with high accuracy.

SUBSMELL: Multimedia with a Simple Olfactory Display

The idea of adding the SubSmell logo to the movie for describing the scent of each event in the movie has been proposed to improve the current way of seeing movies, which can perceive only pictures and sound. Using the SubSmell, the audience can smell the movie. The audiences need a SubSmell application to read a SubSmell and an olfactory display in order to release scent. There are two main parts in SubSmell system, which are an olfactory display and a SubSmell application. An olfactory display consists of a control box and four smell boxes with four fans. Fans will be turned on and release scents when receiving the signal from a SubSmell application. A SubSmell application is designed to read a SubSmell in the movie and decide to send signals to an olfactory display. A SubSmell application consists of four major components: 1) Movie Controlling, 2) SubSmell Reading, 3) Scent Releasing and 4) Olfactory Display Monitoring. We use Microsoft Visual Basic 6.0 to develop the user interface and the SubSmell components. The experiment was done in order to assess the following qualities: 1) Usability: to prove that the system can read a SubSmell in the movie and release scent. 2) Efficiency: to show that the system can work with high accuracy.

Beer classification by electronic nose

An electronic nose is a smart instrument that is designed to detect and discriminate among complex odors by using arrays of sensors. The arrays of sensors are treated with a variety of odor-sensitive biological or chemical materials. An electronic nose is a project that uses two researches areas which are hardware for developing sensors and software using theorem from neuron network technology. The operation begins when sensors hit the smell of beer. The result is converted from analog to digital and represented in a graph form. An artificial intelligence is a tool of a thinking system which can create knowledge as if a human does. This project concerns training and testing beer by using 10 types of beer which are Asahi, Chang, Cheer, Samiguel, Singha, Kloster, Heineken, Leo, Tiger and Tai. We separate the experiment into two parts. The first part is immediate checking, which is performed immediately after the beer can is opened. The second part is to check the beer after the can is opened for 24 hours. This project consists of two data classifications which are Rule base and Neural Network. Rule base is used to classify unknown data. Neural network is used to check types of beer. Our structure in a neural network consists of 25 input nodes, 28 hidden nodes, and 10 output nodes. The percentage of correctness is equal to 87.5%.

Printed Thai Character Recognition by Genetic Algorithm

This research applied a genetic algorithm in the pattern of cellular automata and through Conways rules of the game of life, to generate a system of printed Thai character recognition. The system consisted of two main parts, namely, recognition training and recognition testing. The printed character images fed to the first part were derived from standard character patterns widely used in a computer currently totalling 72, 864 characters. As for the images used for recognition testing, they were captured from a computer screen and stored in BMP pattern, amounting to 1,015 characters. The findings in this research revealed that the database used was of large size and data was transformed from a table frame of 64 x 64 pixels to be stored in the form of bit strings. A table size of 64 x 64 pixels was used to enable a wide variety of distribution patterns of the stable state of each character, making its identity more obvious. This, of course, caused a modification process in each generation till the final generation which took a long time while the database was used to represent the population of the final generation of each character must be large enough for the bit string used to represent these characters. This would enable the system to recognize a character based on its frequency with the largest number of those bit string patterns. Out of 1,015 printed Thai characters tested, it was found that the system could recognize (accept) 986 characters or 97.14 %, while rejecting 6 characters or 0.59 % and misrecognizing 23 characters or 2.27 %. The recognition speed is 85 seconds per character on the average.

Fingerprint Recognition by Euclidean Distance

this research proposed the fingerprint recognition by euclidean distance method. the system uses a technique of image processing, which consists of 3 major components, which are: 1) preprocessing component, the module that reduces the noise of the original images and adjusts the sharpness of the lined pattern that is the components of the fingerprint, 2) feature extraction component, the module that defines the position of the core point used as a reference point and finds out the position of the bifurcation points, and 3) fingerprint recognition component, the module to compare the shape context of training and testing data sets. based on the experimental results, the system has acceptable accuracy with average access time of around 19.68 seconds per image.

Notice of Retraction Instant coffee classification by electronic noses

Normally, an electronic nose project uses two researches areas which are hardware for developing sensors to detect substance smell and software using pattern matching theorem for recognizing substance. For this research, the operation begins with sensors hit the coffee smell. The result is converted from analog to digital representation. An artificial intelligence is a tool of a thinking system which can create knowledge as if a human does. The objective of this research is to classify instant coffee by using electronic noses. We used eight types of coffee in Thailand market for this project which are (1) Moccona-select, (2) Moccona-royal gold, (3) Nescafe redcup, (4) Nescafe gold, (5) Khao Shong brown, (6) Khao Shong red, (7) Oem-Big C and (8) Superclass. We compared four structures of neural network to classify the coffee data. The precision of correctness is equal to 65.63 for a neural network structure as 7 input-layer nodes, 14 hidden-layer1 nodes, 48 hidden-layer2 nodes and 8 output-layer nodes.

Smart Scarecrow

Thailand is an agricultural country, where is located in Southeast Asia. We can produce various kinds of food in not only a good quality but also a huge quantity. One problem of both quality and quantity control of our food products are the food harmful pests such as bird, ant, weevil, aphid, grasshopper etc. Therefore, this project intends to develop the computer system that can be chased birds from a farm. The smart scarecrow is developed by using an image processing technique. Overall works are software development. The system is designed to detect pest birds from a real time video frame after it detects the birds then it generates a loudly sound to chase them. The system consists of four major components: 1) image acquisition 2) image preprocessing, 3) bird recognition and 4) generating sound. The experiment has been conducted in order to access the following qualities: 1) usability, to prove that the system can detect and scare pest birds and 2) efficiency, to show that the system can work with a high accuracy.

Thai Handwritten Character Recognition by Euclidean Distance

This research applied the Euclidean distance technique to generate a system of Thai handwritten character recognition. The system consists of four main components which include: 1) Image Acquisition, 2) Image Pre-processing, 3) Recognition, and 4) Display Result. All training and testing handwritten characters in this research used all Thai native people to write them for avoiding invalid shape of Thai character. The character images fed to the training part totaling 3,513 characters. Out of 878 Thai handwritten characters tested, it was found that the system could recognize (accept) 716 characters or 81.55%, while rejecting 61 characters or 6.95% and misrecognizing 101 characters or 11.50%. We tested the system with 50 Japanese handwritten characters and 25 invalid Thai handwritten character shape, it was found that the system could reject 47 characters or 62.67% while misrecognizing 28 characters or 37.33%.

A Dictionary-Based Approach for Thai Text to Speech (TTTS)

The idea of text to speech by a computer is an enhancement of the human learning ability. Due to the fact that each person has individual ability of visualization, the receiving of information in the form of voice helps make everything become easier. The objective of this research is to develop computer software that can translate Thai Text to Speech (TTTS). The TTTS consists of four modules, which are 1) Input Thai text file, 2) Text processing, 3) Dictionary Lookup, and 4) Speech synthesis. The TTTS dictionary contains more than 5,300 Thai primitive words and their sound waves. The experiment is conducted on 30 Thai text files, which contain more than 3200 Thai words. The reading precision of the TTTS is around 74.05 percent, with the reading speech of 0.88 second per word.