Zhe X Lin563 Lorimer St, Brooklyn, NY 11211

2016030, Oct 20, 2016

Jun 29, 2016

15/196478

- San Jose CA, US
Haoxiang Li - Kearny NJ, US
Zhe Lin - Fremont CA, US
Jonathan W. Brandt - Santa Cruz CA, US

Adobe Systems Incorporated - San Jose CA

G06K 9/66
G06K 9/00
G06K 9/46

Different candidate windows in an image are identified, such as by sliding a rectangular or other geometric shape of different sizes over an image to identify portions of the image (groups of pixels in the image). The candidate windows are analyzed by a set of convolutional neural networks, which are cascaded so that the input of one convolutional neural network layer is based on the input of another convolutional neural network layer. Each convolutional neural network layer drops or rejects one or more candidate windows that the convolutional neural network layer determines does not include an object (e.g., a face). The candidate windows that are identified as including an object (e.g., a face) are analyzed by another one of the convolutional neural network layers. The candidate windows identified by the last of the convolutional neural network layers are the indications of the objects (e.g., faces) in the image.

2016014, May 26, 2016

Nov 20, 2014

14/549350

- San Jose CA, US
Haoxiang Li - Kearny NJ, US
Zhe Lin - Fremont CA, US
Jonathan W. Brandt - Santa Cruz CA, US

G06K 9/66
G06K 9/46
G06K 9/62
G06N 3/04

A convolutional neural network is trained to analyze input data in various different manners. The convolutional neural network includes multiple layers, one of which is a convolution layer that performs a convolution, for each of one or more filters in the convolution layer, of the filter over the input data. The convolution includes generation of an inner product based on the filter and the input data. Both the filter of the convolution layer and the input data are binarized, allowing the inner product to be computed using particular operations that are typically faster than multiplication of floating point values. The possible results for the convolution layer can optionally be pre-computed and stored in a look-up table. Thus, during operation of the convolutional neural network, rather than performing the convolution on the input data, the pre-computed result can be obtained from the look-up table

2016014, May 26, 2016

Nov 21, 2014

14/550800

- San Jose CA, US
Haoxiang Li - Kearny NJ, US
Zhe Lin - Fremont CA, US
Jonathan W. Brandt - Santa Cruz CA, US

G06K 9/66
G06K 9/62
G06K 9/46

Different candidate windows in an image are identified, such as by sliding a rectangular or other geometric shape of different sizes over an image to identify portions of the image (groups of pixels in the image). The candidate windows are analyzed by a set of convolutional neural networks, which are cascaded so that the input of one convolutional neural network layer is based on the input of another convolutional neural network layer. Each convolutional neural network layer drops or rejects one or more candidate windows that the convolutional neural network layer determines does not include an object (e.g., a face). The candidate windows that are identified as including an object (e.g., a face) are analyzed by another one of the convolutional neural network layers. The candidate windows identified by the last of the convolutional neural network layers are the indications of the objects (e.g., faces) in the image.