New in Image Processing
Version 12 continues to utilize modern machine learning and neural networks to add state-of-the-art, high-level, efficient computer vision functions for object detection and recognition, facial analysis, text recognition segmentation and many more. In addition, a large number of new functions and updates have been introduced to enable easier workflow of applications in research and development, computational photography, microscopy, astronomy, medicine and more.
- Expanded built-in computer vision functions. »
- Automated object detection and recognition. »
- Improved face detection and facial feature analysis. »
- Improved and controllable text recognition. »
- Built-in image style transfer using one or more templates. »
- Immediately accessible pre-trained neural nets for images. »
- Support for image pyramids for multiscale processing. »
- Specification of color neighborhoods for smooth color segmentation. »
- Expanded color analysis & processing for image recoloring. »
- Improved and new color quantization methods. »
- Automated brightness equalization to correct for uneven illumination. »
- Conversion of images to vector graphics. »
- Rasterization of 2D and 3D regions into images. »
- Addition of new types of image keypoints. »
- Immediate support for image arithmetic and statistical operations. »
- Updated the internal storage of image data. »
