Markany Inc.

So Won Kim

Min Soo Park

Ji Seop Moon

Tai Yoon Lee

Euee Seon Jang

Dong Young Lee

Hyungyu Kim

Seung Yeob Chae

Dong Hwan Shin

Kun Tae Kim

Gyeong Gi Noh

Provided is an artificial neural network learning apparatus for deep learning. The apparatus includes an input unit configured to acquire an input data or a training data, a memory configured to store the input data, the training data, and a deep learning artificial neural network model, and a processor configured to perform computation based on the artificial neural network model, in which the processor sets the initial weight depending on the number of nodes belonging to a first layer and the number of nodes belonging to a second layer of the artificial neural network model, and determines the initial weight by compensation by multiplying a standard deviation (&#x3c3;) by a square root of a reciprocal of a probability of a normal probability distribution for a remaining section except for a section in which an output value of the activation function converges to a specific value.

Weight initialization method and apparatus for stable learning of deep learning model using activation function

Provided is a method for reconstructing content image data. The method includes selecting a first point and a second point in a first image of first content, selecting a third point and a fourth point in a second image of second content (the second image is an image corresponding to the first image and the third point and the fourth point are points in an image corresponding to the first point and the second point, respectively), generating a first reference vector using the first point and the second point, generating a second reference vector using the third point and the fourth point, calculating a rotation, scale, and transformation (RST) value from the first image to the second image using the first reference vector and the second reference vector; and reconstructing the second content using the calculated RST value.

Method and apparatus for reconstructing content image data

One aspect of the present invention discloses an apparatus for detecting additional data for preventing forgery of video data and displaying the video content. The apparatus includes a content input unit configured to receive the video content (the video content including the additional data), a display unit configured to display the video content, an additional data detector configured to detect the additional data from the video content (the additional data including a watermark), and a display controller configured to control a display screen of the video content according to an additional data detection result.

Apparatus, method and system for detecting additional data for preventing forgery of video content, rendering apparatus interoperating with display apparatus, and rendering method thereof

A method and apparatus for watermarking digital content and a data extraction method are disclosed. The digital content watermarking method includes: generating private and public keys corresponding to the user terminal; generating watermark data containing user identity information corresponding to the user terminal and user details associated with the watermark data; generating encrypted data by encrypting the watermark data and the user details with the private key; transmitting the watermark data, the encrypted data, and the public key to a server; receiving digital content when authorized by the server; and watermarking the digital content with the watermark data.

Method and apparatus for watermarking of digital content, method for extracting information

A method of inserting additional data into a moving image stream, according to some embodiments of the present invention, includes receiving a first coded bitstream, electing a first picture PA into which additional data is to be inserted from the first coded bitstream, generating a first picture PA' by inserting the additional data into the selected first picture PA, selecting a second picture PB directly referring to the first picture PA, generating a second picture PB&#x2032; by transforming and coding the selected second picture PB in a manner that decoding the second picture PB&#x2032; obtains the second picture PB with reference to the first picture PA&#x2032; and generating a data sequence based on the first picture PA&#x2032; and the second picture PB.

Method and apparatus for inserting additional data into video stream without degrading picture quality

Disclosed is a watermark embedding method. The method includes receiving an original image, generating a watermark image based on the selected watermark pattern, generating an alpha blended stego image by alpha blending the original image and the watermark image, and providing the alpha blended stego image, in which the watermark image is generated by considering at least one of allowable pixel value range and alpha value &#x3b1; range of the watermark pattern applied to a first pixel of the original image, wherein the at least one of allowable pixel value range and alpha value &#x3b1; range are determined by the difference of pixel value of the first pixel between the original image and the stego image by embedding the watermark pattern to the first pixel.

Watermark embedding method and apparatus, and system

One aspect of the present invention discloses a watermark embedding method. The method includes: inputting an original bitstream; determining a first frame for embedding a watermark in the input original bitstream; selecting one of frames after the first frame as a second frame; generating the first frame a bidirectional-coded frame (B frame) referring to the second frame; generating the second frame as a reference frame of the first frame; and embedding the watermark in the first frame generated as the B frame.

Watermark embedding apparatus and method through image structure conversion

Provided are an apparatus and a method for detecting a scene cut frame. The apparatus and a method for detecting a scene cut frame includes an image selector configured to select input images by n image frames while shifting an input image at h frame intervals; a candidate frame detector configured to detect a candidate frame from the selected n image frames using at least one of a plurality of codecs and a plurality of scene cut detecting algorithms; and a final frame detector configured to detect a frame having a count value higher than a threshold value as a final scene cut frame by performing histogram analysis based on the detected candidate frame, wherein the h and the n are a real number greater than zero and the h is smaller than the n.

Growing community of inventors

Seoul, South Korea

So Won Kim