Why would neural networks may gain more from raw images than jpeg?

In today's post, we are going to quickly find out why we should prefer raw images vs frequently used jpeg images when training neural nets. But before we jump into why raw images, let's first quickly revisit what JPEG images are and how they are generated. According to Wikipedia, JPEG or JPG is a commonly used method of lossy compression for digital images, particularly for those images produced by digital photography. Essentially, what it means is that while you are taking a photograph using your camera (say, mobile phone camera), the camera post-processor will automatically do some processing to "compress" the image to reduce its file size or memory footage without any perceivable quality degradation. It is these Discrete Cosine Transform (DCT) and Quantization stages that essentially affects or manipulates the ultimate image intensity values.