According to Huawei, the HiAI engine can extend application functions, integrate multiple AI functions, and make applications more intelligent and powerful. ' Developers can now download DDK (Driver Development Kit), SDK and IDE HiAI engine.
One of the highlights of the application function of the HiAI engine is the computer vision (CV) engine. The computer vision engine refers to the 'computer's ability to simulate the human visual system to perceive the surrounding environment, determine, identify and understand the spatial composition'. The functions of the CV engine include Image super-resolution, facial recognition and object recognition.
The HiAI engine also includes an Automatic Speech Recognition (ASR) engine. The engine is only available in China. The ASR engine is a function that converts human voices into text. Its functions include speech recognition, speech conversion, and text-to-speech (TTS).
The Natural Language Understanding (NLU) engine is also part of the HiAI engine's functionality, but like the ASR engine, it is only open to Chinese territory. It enables computers to understand the human voice, which enables them to communicate or act in nature. Its functions include word segmentation. , text entity recognition, emotional tendency analysis and machine translation.
The HiAI engine has the following features:
Scene detection: It 'fast-classify' images by identifying scenes in the image content. Huawei stated that the current support for recognition of multiple scenes has high accuracy.
File Correction and File Detection: This is an auxiliary enhancement that can correct the angle of the document. It can also automatically identify the position of the document in the image.
Face Detection and Face Comparison: According to Huawei, in face detection, information on face position, feature points, and posture in a given image is detected, and high-precision facial orthogonal coordinates are returned.
Image classification tag: Based on deep learning method, identify objects, scenes and behaviors in the image.
Image Super Resolution: Huawei claims that it can intelligently enlarge images based on deep learning. It can also obtain sharper, clearer images without changing the resolution.
Feature image super-resolution: The image containing features can be enlarged 9 times. It can also 'enhance' characters on images.
Code detection: According to Huawei, code detection obtains the information contained in the code by reading the quick response (QR) code and bar code, which in turn provides related services. The code detection function is integrated in the application.