2. If the camera on the back is turned on, it may be that your mobile phone model is too new and the direct banking APP is temporarily incompatible. You can invite others to hold your mobile phone to help you complete face recognition.
Face recognition fails for several reasons:
Network status: the device is not connected to the network, or the signal is too poor to upload the input data to the terminal and execute the next instruction.
Lighting conditions: In face recognition, the environment is dark, and the equipment cannot clearly distinguish faces.
Software version: the system pushes the latest software version, but the equipment is not updated, which affects the data transmission to the terminal.
Factors affecting face recognition
1. illumination problem, illumination change is the most critical factor affecting the performance of face recognition, and the degree of solving this problem is related to the success or failure of the practical process of face recognition. .
2. Attitude problem, face recognition is mainly based on facial features, and how to identify facial changes caused by posture has become one of the difficulties of this technology.
3. Expression problems, such as crying, laughing, anger and other large facial expression changes also affect the accuracy of facial recognition.
4. Occlusion is a very serious problem for face image acquisition under non-cooperative conditions.
5. Age changes. With the change of age, a person may change from a teenager to an old man, and his appearance may change greatly, resulting in a decline in recognition rate.
6. Facial similarity, there is little difference between different individuals, all facial structures are similar, and even the structure and appearance of facial organs are similar.
7. Dynamic identification. In the case of uncoordinated face recognition, the blurred face image caused by motion or incorrect camera focus will seriously affect the success rate of face recognition.
8. Face anti-counterfeiting, the mainstream deception means of forging face images for recognition is to establish a three-dimensional model or graft some expressions.
9. Due to the lack of samples, the face recognition algorithm based on statistical learning is the mainstream algorithm in the field of face recognition at present, but the statistical learning method needs a lot of training.
10. Image quality. The sources of facial images can be varied. Due to different acquisition equipment, the quality of the obtained face images is also different, especially the face images with low resolution, high noise and poor quality.
Face authentication needs to meet the following conditions:
1. The certificate type of registered bank e-banking or bank card is ID card;
2. The bank counter of a bank has handled the transaction that needs to verify the identity card;
Please ensure that the face is in the designated area of the screen under the condition of sufficient light and smooth network, and follow the prompts at the bottom of the screen to complete the designated action. If you have any other questions, you can consult the online customer service of China Bank.
Minsheng bank v6.03