a comparative analysis on various block truncation methods in the e-learning environment

Image compression and image processing are the two aspects that affect image specific e-learning environment. in this regard, there are various methods proposed to process and compress the image effectively. recent works mainly concentrate on finding the memory complexity and processing complexity of various techniques. according to that, block truncation models are widely applied over various e-learning fields. block truncation model (btm) considers the images as a collection of individual blocks to be processed. these blocks are extracted and evaluated for image compression. to compress the images, the least important blocks need to be ignored or suppressed. at this stage, standard btc, absolute moment btc (ambtc), machine learning (ml) based btc and deep learning (dl) based btc techniques have emerged from various resources. this work is analyzing various btc models in terms of time efficiency, memory efficiency and computation efficiency. the results shown in this work reveal the detailed comparisons of e-learning based block truncation models.