Lossless image compression using neural network

The purpose of the project is to assess the feasibility of using Neural Network as the prediction mechanism for lossless compression of images. The Neural Network model used is the Multilayer Perceptron or the Backpropagation model with one input layer, one hidden layer and one output layer. The ima...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Chin, Heng Ee.
مؤلفون آخرون: Soon, Ing Yann
التنسيق: Theses and Dissertations
اللغة:English
منشور في: 2009
الموضوعات:
الوصول للمادة أونلاين:http://hdl.handle.net/10356/19781
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
المؤسسة: Nanyang Technological University
اللغة: English
الوصف
الملخص:The purpose of the project is to assess the feasibility of using Neural Network as the prediction mechanism for lossless compression of images. The Neural Network model used is the Multilayer Perceptron or the Backpropagation model with one input layer, one hidden layer and one output layer. The image used for compression is a SPOT Multispectral Satellite image with three image bands: Green, Red and Infra-Red. In this project, both intra band and inter band predictive coding were implemented. In intra-band prediction, samples from the same single band are used to predict the sample to be coded. However, for inter band prediction, samples from more than one band are used.