Endoscopy images are often constrained by poor color representation. To obtain results that do not alter the image color and quality during effective enhancement, this work proposes a color enhancement algorithm based on color intensity using convolutional neural networks (CNNs) on endoscopic images. The overall process of the algorithm is constructed based on the color loss and uneven color loss phenomena during the endoscopic imaging process. First, to address the issue of color uniformity, this work generates a training set through Gaussian blurring, random attenuation, and image partitioning. It proposes a CNN with four layers that have different training structures and mapping output structures for generating the color intensity map of an image. Second, to tackle the problem of color intensity, a channel loss function is introduced to restore the color intensity of the green and blue channels of the endoscopic image. To address the issue of poor color contrast, histogram equalization under limited contrast is introduced to enhance the contrast of each channel of the endoscopic image. Finally, an image fusion strategy is proposed to merge the channel intensity restoration and contrast enhancement maps with the original image based on the color intensity map.