Handwritten Number Recognition / News: Recent posts

An image searching system was developed by using image processing and neural network technique. Given a single image, the system is able to search out all the images with high similarity from an image database.

SOM2D demo applet 0.01 is released.

library for SOM2D neural network is released. this is an initial creation.

Added getHistogram and getHSBHistogram.

libnumrecognition is a Java library created for handwritten digit recognition purpose. With the default neural network model shipped together with libnumrecognition, the highest recognition rate is 97.87% and the lowest recognition rate is 90.92%.

Currently, libnumrecognition is in the preliminary state. It can only accept images in the noiseless, single/ multiple digit form. However, development work on libnumrecognition is still going on. libnumrecognition is hoped to be evolved into a complete digit recognition framework, which can accept images with noisy background, multiple objects form. Only with that capability, we are able to use libnumrecognition to solve real world problem.... read more

Handwritten Number Recognition Release 1.1.2

Handwritten Number Recognition New Release 1.1.1 Is Ready