Hon Hai Precision Industry Co., Ltd.

Foxconn Technology Group Co., Ltd.

Hong-fu Jin Precision Industry (shenzhen) Co., Ltd.

Yung-Hui Li

Chi-En Huang

Hong-Han Shuai

Nien-yi Jan

Ting-Hsuan Lee

Yen-Cheng Lin

Wei-Bin Lee

Kai-Lin Yang

Guo-Dong Su

Yan-Jun Liu

Muhammad Saqlain Aslam

Jing-Cheng Ke

Jia Wang

Wen-Huang Cheng

Van Nhiem Tran

Shen-Hsuan Liu

Wenny Ramadha Putri

An image augmentation device is provided, which includes a memory and a processor. The processor is configured for performing following operations: extracting a first object contour from a first image mask, wherein the first object contour corresponds to a first label; superimposing the first object contour to a superimposed region in a second image mask according to an augmentation parameter to generate a third image mask, wherein the augmentation parameter includes a contour scaling parameter, a contour moving distance, a contour rotation angle and a range which can be superimposed, and the third image mask includes the first object contour and a second object contour in the second image mask; and generating a sample image which corresponds to according to the first object contour and the second object contour in the third image mask by a generative adversarial network model for performing machine learning.

Image augmentation device and method

A data augmentation device including a processor is disclosed. The processor is configured to capture at least one sample image from an original image, and the processor is configured to input the at least one sample image to at least two data augmentation module, so as to generate at least two augmentation image group through the at least two data augmentation module. The at least two data augmentation module include a first data augmentation module and a second data augmentation module, in which a first parameter group of the first data augmentation module is a fixed value, and a second parameter group of the second data augmentation module is not the fixed value.

Data augmentation device, method, and non-transitory computer readable storage medium

A recognition method includes the following steps. A text is analyzed by a language recognition network to generate an entity feature, a relation feature and an overall feature. An input image is analyzed by an object detection network to generate candidate regions. Node features, aggregated edge features and compound features are generated by an enhanced cross-modal graph attention network according to the entity feature, the relation feature, the candidate regions and the overall feature. The entity feature and the relation feature are matched to the node features and the aggregated edge features to generate the first scores. The overall feature is matched to the compound features to generate second scores. Final scores corresponding to the candidate regions are generated according to the first scores and the second scores.

Recognition method and electronic device

An image processing device is provided, which includes an image capture circuit and a processor. The image capture circuit is configured to capture a low-resolution image. The processor is connected to the image capture circuit and executes a super-resolution model (SRM), wherein the SRM includes multiple neural network blocks, and the processor is configured to perform the following operations: generating a super-resolution image from the low-resolution image by using the multiple neural network blocks, where one of the multiple neural network blocks includes a spatial attention model (SAM) and a channel attention model (CAM), the CAM is concatenated after the SAM, and the SAM and the CAM are configured to enhance a weight of a region in the super-resolution image, which is covered by a region of interest in the low-resolution image. In addition, an image processing method is also disclosed herein.

Image processing device and method

An image processing device is provided, which includes an image capture circuit and a processor. The image capturing circuit is configured for capturing a high-resolution image. The processor is connected to the image capturing circuit, and performing a super-resolution model and an attention model, where the processor is configured to perform following operations for: performing down sampling processing on the high-resolution image to generate a low-resolution image; performing super-resolution processing on the low-resolution image using the super-resolution model to generate a super-resolution image; applying the attention model to the high-resolution image and the super-resolution image to generate an attention weighted high-resolution image and an attention weighted super-resolution image, and calculating a first loss according to the attention weighted high-resolution image and the attention weighted super-resolution image, thereby updating the super-resolution model.

Image processing device and super-resolution processing method

An encryption and decryption system is provided, which includes a transmitting device and a receiving device. The transmitting device is configured to store original images and a correspondence table. The receiving device is connected to the transmitting device for storing the correspondence table, wherein the transmitting device generates an encrypted string. The transmitting device selects a representative morphed image from multiple morphed images according to the encrypted string. The transmitting device transmits the representative morphed image to the receiving device and does not transmit the encrypted string to the receiving device. The receiving device recognizes the first original image serial number and the second original image serial number from the representative morphed image. The receiving device looks up the correspondence table according to the first original image serial number and the second original image serial number to generate the encrypted string.

Encryption and decryption system and method

A model generating apparatus and method are provided. The apparatus receives a plurality of sample images. The apparatus generates a plurality of adversarial samples corresponding to the sample images. The apparatus inputs the sample images and the adversarial samples respectively to a first encoder and a second encoder in a self-supervised neural network to generate a plurality of first feature extractions and a plurality of second feature extractions. The apparatus calculates a similarity of each of the first feature extractions and the second feature extractions to train the self-supervised neural network. The apparatus generates a task model based on the first encoder and a plurality of labeled data.

Growing community of inventors

Taipei, Taiwan

Yung-Hui Li