公开(公告)号：US20150160839A1

公开(公告)日：2015-06-11

申请号：US14099797

申请日：2013-12-06

Applicant: Google Inc.

Inventor： Aravind Krishnaswamy ,  David Gary Besbris

IPC: G06F3/0484 ,  G06F3/0482

CPC classification number: G06F3/04845 ,  G06F3/0482

Abstract: Implementations relate to editing options for image regions. Some implementations include detecting a region portion of an image based on one or more characteristics of pixels of the image. The detected region has an identified class selected from multiple identifiable classes, and each identifiable class is associated with a set of multiple editing options. Each editing option is associated with edit operation(s) operable to adjust value(s) of one or more image pixels. One of the sets of editing options is presented for selection, where the presented set is associated with the identified class of the detected region and each of the editing options in the presented set is operable to adjust value(s) of one or more pixels of the detected region. The presented set of editing options is different from at least one of the other sets of editing options associated with the other classes.

Abstract translation: 实现涉及图像区域的编辑选项。 一些实现包括基于图像的像素的一个或多个特征来检测图像的区域部分。 检测到的区域具有从多个可识别类中选择的识别类，并且每个可识别类与一组多个编辑选项相关联。 每个编辑选项与可操作以调整一个或多个图像像素的值的编辑操作相关联。 提供了一组编辑选项用于选择，其中所呈现的集合与所识别的类别的检测到的区域相关联，并且所呈现的集合中的每个编辑选项可操作以调整一个或多个像素的值 检测到的区域。 所提出的编辑选项集不同于与其他类相关联的至少一个编辑选项集合中的至少一个。

公开(公告)号：US20140341442A1

公开(公告)日：2014-11-20

申请号：US13894384

申请日：2013-05-14

Applicant: Google Inc.

Inventor： Justin Lewis ,  Gavin James ,  Grayson Lang ,  Aravind Krishnaswamy ,  Sevket Derin Babacan

IPC: G06T5/00 ,  G06K9/00

CPC classification number: G06K9/00234 ,  G06K9/00248 ,  G06K9/342 ,  G06K9/4652 ,  G06T5/002 ,  G06T5/008 ,  G06T7/11 ,  G06T7/194 ,  G06T2207/10024 ,  G06T2207/30201

Abstract: In some implementations, a method includes identifying one or more face regions of an image, the face regions including pixels that depict at least a portion of one or more faces of persons. The face regions are identified based on identifying facial landmarks of the faces. The method determines an associated face mask for each of the faces based on the face regions, where each face mask indicates which pixels in the image depict the corresponding face. Face pixels can be selected for processing by applying the face masks, and image pixels outside the faces can be selected by inversely applying the face masks. The selected pixels can be provided to a processing operation for adjustment of the selected pixels.

Abstract translation: 在一些实现中，一种方法包括识别图像的一个或多个面部区域，所述面部区域包括描绘人的一个或多个面部的至少一部分的像素。 基于识别面部的面部标志来识别面部区域。 该方法基于面部区域确定每个面部的相关面罩，其中每个面罩指示图像中的哪些像素描绘对应的面部。 可以通过应用面罩来选择面部像素进行处理，并且可以通过反面应用面罩来选择面部之外的图像像素。 可以将所选择的像素提供给用于调整所选像素的处理操作。