Image compression plays an important role in reducing the size and storage of data while increasing the speed of its transmission through the Internet significantly. Image compression is an important research topic for several decades and recently, with the great successes achieved by deep learning in many areas of image processing, especially image compression, and its use is increasing Gradually in the field of image compression. The deep learning neural network has also achieved great success in the field of processing and compressing various images of different sizes. In this paper, we present a structure for image compression based on the use of a Convolutional AutoEncoder (CAE) for deep learning, inspired by the diversity of human eyes' observation of the different colors and features of images. We propose a multi-layer hybrid system for deep learning using the unsupervised CAE architecture and using the color clustering of the K-mean algorithm to compress images and determine their size and color intensity. The system is implemented using Kodak and Challenge on Learned Image Compression (CLIC) dataset for deep learning. Experimental results show that our proposed method is superior to the traditional compression methods of the autoencoder, and the proposed work has better performance in terms of performance speed and quality measures Peak Signal To Noise Ratio (PSNR) and Structural Similarity Index (SSIM) where the results achieved better performance and high efficiency With high compression bit rates and low Mean Squared Error (MSE) rate the results recorded the highest compression ratios that ranged between (0.7117 to 0.8707) for the Kodak dataset and (0.7191 to 0.9930) for CLIC dataset. The system achieved high accuracy and quality in comparison to the error coefficient, which was recorded (0.0126 to reach 0.0003) below, and this system is onsidered the most quality and accurate compared to the methods of deep learning compared to the deep learning methods of the autoencoder
Fractal image compression gives some desirable properties like fast decoding image, and very good rate-distortion curves, but suffers from a high encoding time. In fractal image compression a partitioning of the image into ranges is required. In this work, we introduced good partitioning process by means of merge approach, since some ranges are connected to the others. This paper presents a method to reduce the encoding time of this technique by reducing the number of range blocks based on the computing the statistical measures between them . Experimental results on standard images show that the proposed method yields minimize (decrease) the encoding time and remain the quality results passable visually.
Deep learning convolution neural network has been widely used to recognize or classify voice. Various techniques have been used together with convolution neural network to prepare voice data before the training process in developing the classification model. However, not all model can produce good classification accuracy as there are many types of voice or speech. Classification of Arabic alphabet pronunciation is a one of the types of voice and accurate pronunciation is required in the learning of the Qur’an reading. Thus, the technique to process the pronunciation and training of the processed data requires specific approach. To overcome this issue, a method based on padding and deep learning convolution neural network is proposed to
... Show More
(18)
(2)
(16)
(13)
In this paper three techniques for image compression are implemented. The proposed techniques consist of three dimension (3-D) two level discrete wavelet transform (DWT), 3-D two level discrete multi-wavelet transform (DMWT) and 3-D two level hybrid (wavelet-multiwavelet transform) technique. Daubechies and Haar are used in discrete wavelet transform and Critically Sampled preprocessing is used in discrete multi-wavelet transform. The aim is to maintain to increase the compression ratio (CR) with respect to increase the level of the transformation in case of 3-D transformation, so, the compression ratio is measured for each level. To get a good compression, the image data properties, were measured, such as, image entropy (He), percent root-
... Show MoreIn this paper three techniques for image compression are implemented. The proposed techniques consist of three dimension (3-D) two level discrete wavelet transform (DWT), 3-D two level discrete multi-wavelet transform (DMWT) and 3-D two level hybrid (wavelet-multiwavelet transform) technique. Daubechies and Haar are used in discrete wavelet transform and Critically Sampled preprocessing is used in discrete multi-wavelet transform. The aim is to maintain to increase the compression ratio (CR) with respect to increase the level of the transformation in case of 3-D transformation, so, the compression ratio is measured for each level. To get a good compression, the image data properties, were measured, such as, image entropy (He), percent r
... Show MoreThere are many images you need to large Khoznah space With the continued evolution of storage technology for computers, there is a need nailed required to reduce Alkhoznip space for pictures and image compression in a good way, the conversion method Alamueja
(2)
(14)
(15)
(31)
(31)
In this paper, a method is proposed to increase the compression ratio for the color images by
dividing the image into non-overlapping blocks and applying different compression ratio for these
blocks depending on the importance information of the block. In the region that contain important
information the compression ratio is reduced to prevent loss of the information, while in the
smoothness region which has not important information, high compression ratio is used .The
proposed method shows better results when compared with classical methods(wavelet and DCT).