image-segmentation

问题 I am doing a image segmentation task based on deep convolutional neural network. The network structure is from this paper, and the structure can be seen in the picture:FCN used in image segmentation. The network is designed based on Fully Convolutional Network and DCAN. The data set is the public benchmark dataset of Gland Segmentation Chalenge Contest in MICCAI 2015(also named as Warwick-QU dataset.) I use this network to do the segmentation task. However in my result, I always noticed a

问题 I am doing a image segmentation task based on deep convolutional neural network. The network structure is from this paper, and the structure can be seen in the picture:FCN used in image segmentation. The network is designed based on Fully Convolutional Network and DCAN. The data set is the public benchmark dataset of Gland Segmentation Chalenge Contest in MICCAI 2015(also named as Warwick-QU dataset.) I use this network to do the segmentation task. However in my result, I always noticed a

问题 This is my very first time using a Convolutional Neural Networks and Tensorflow. I am trying to implement a convolutional neural network that is able to extract vessels from Digital Retinal Images. I am working with the publicly available Drive database (images are in .tif format). Since my images are very large my idea is to split them into sub-images of size 28x28x1 (The "1" is the green channel, the only one I need). To create the training set I randomly crop a 28x28 batch iteratively from

问题 Let's say I have two binary images of the same size. How do I find the intersection between the two binary images? Only pixels of the same coordinate (location) on the two images that are white (gray - 255) will give white pixels on the output image (intersection). 回答1: You can use cvAnd or cv::bitwise_and on the two images. The resulting image will be white only where both the input images are white. EDIT: Here are the results of applying cv::bitwise_and, cv::bitwise_or and cv::bitwise_xor

问题 I am reading a lot of tutorials that state two things. "[Replacing fully connected layers with convolutional layers] casts them into fully convolutional networks that take input of any size and output classification maps." Fully Convolutional Networks for Semantic Segmentation, Shelhamer et al. A traditional CNN can't do this because it has a fully connected layer and it's shape is decided by the input image size. Based on these statements, my questions are the following? Whenever I've made a

问题 I am trying to implement a U-Net with Keras with Tensorflow backend for an image segmentation task. I have images of size (128,96) as input to the network together with mask images of size (12288,6) since they are flattened. I have 6 different classes (0-5) which gives the second part of the mask images' shape. They have been encoded to one-hot labels using the to_categorical() function. At the moment I use just one input image and also use the same one as validation and test data. I would

问题 I wanted to run the Deconvnet on my data, however it seemd it has been written for another version of caffe . Does anyone know how to change batch_params ? The one that is in Deconvnet layers { bottom: 'conv1_1' top: 'conv1_1' name: 'bn1_1' type: BN bn_param { scale_filler { type: 'constant' value: 1 } shift_filler { type: 'constant' value: 0.001 } bn_mode: INFERENCE } } And the one that Caffe provides for cifar10 example: layer { name: "bn1" type: "BatchNorm" bottom: "pool1" top: "bn1" batch

问题 Hi I would like to segment objects in a video sequence based on optical flow (as suggested in this answer), I am using opencv and have been able to generate a flow field for two successive frames using the calcOpticalFlowFarneback function. Could someone explain how I would go about segmenting an image based on this flow field? 回答1: Since you want to use Optical Flow to segment object so your decision making will be based on the type of motion your objects under go...You can have a look at

问题 I want to create a custom loss layer for semantic segmentation in caffe that requires multiple inputs. I wish this loss function to have an additional input factor in order to penalize the miss detection in small objects. To do that I have created an image GT that contains for each pixel a weight. If the pixel belongs to a small object the weight is high. I am newbie in caffe and I do not know how to feed my net with three 2-D signals at the same time (image, gt-mask and the per-pixel weights

问题 I've read the documentation for calcHist() many times, but I think my inexperience with OpenCV and rusty programming skills are completely precluding me from understanding it. I'm looking to count pixels in one channel of an HSV image (Hue, or channel[0]) for segmentation purposes using 10 bins that closely approximate color according to something like (let's use this as an example, I stole the ranges off the web - fwiw, it seems erroneous to omit purple-red): Red: 0-19 & 330-360 Red-Yellow