# DCT-CompCNN: A Novel Image Classification Network Using JPEG Compressed DCT Coefficients

arXiv: https://arxiv.org/abs/1907.11503 · HTML: https://mlsanity.com/paper/1907.11503/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jul 2019.

## Built on by (most cited first, 11 of 11)

- [An Introduction to Neural Data Compression](https://mlsanity.com/paper/2202.06533/) (2022)
- [RGB no more: Minimally-decoded JPEG Vision Transformers](https://mlsanity.com/paper/2211.16421/) (2022)
- [DCT-Former: Efficient Self-Attention with Discrete Cosine Transform](https://mlsanity.com/paper/2203.01178/) (2022)
- [Detection of Plant Leaf Disease Directly in the JPEG Compressed Domain using Transfer Learning Technique](https://mlsanity.com/paper/2107.04813/) (2021)
- [T2CI-GAN: Text to Compressed Image generation using Generative Adversarial Network](https://mlsanity.com/paper/2210.03734/) (2022)
- [Deep Learning Based Image Retrieval in the JPEG Compressed Domain](https://mlsanity.com/paper/2107.03648/) (2021)
- [DWT-CompCNN: Deep Image Classification Network for High Throughput JPEG 2000 Compressed Documents](https://mlsanity.com/paper/2306.01359/) (2023)
- [Document Image Binarization in JPEG Compressed Domain using Dual Discriminator Generative Adversarial Networks](https://mlsanity.com/paper/2209.05921/) (2022)
- [OCR for TIFF Compressed Document Images Directly in Compressed Domain Using Text segmentation and Hidden Markov Model](https://mlsanity.com/paper/2209.09118/) (2022)
- [CompTLL-UNet: Compressed Domain Text-Line Localization in Challenging Handwritten Documents using Deep Feature Learning from JPEG Coefficients](https://mlsanity.com/paper/2308.06142/) (2023)
- [CNNs for JPEGs: A Study in Computational Cost](https://mlsanity.com/paper/2309.11417/) (2023)

## Abstract (arXiv)

The popularity of Convolutional Neural Network (CNN) in the field of Image Processing and Computer Vision has motivated researchers and industrialist experts across the globe to solve different challenges with high accuracy. The simplest way to train a CNN classifier is to directly feed the original RGB pixels images into the network. However, if we intend to classify images directly with its compressed data, the same approach may not work better, like in case of JPEG compressed images. This research paper investigates the issues of modifying the input representation of the JPEG compressed data, and then feeding into the CNN. The architecture is termed as DCT-CompCNN. This novel approach has shown that CNNs can also be trained with JPEG compressed DCT coefficients, and subsequently can produce a better performance in comparison with the conventional CNN approach. The efficiency of the modified input representation is tested with the existing ResNet-50 architecture and the proposed DCT-CompCNN architecture on a public image classification datasets like Dog Vs Cat and CIFAR-10 datasets, reporting a better performance