java分水岭分割_java - 如何使用分水岭来改善图像分割？ - SO中文参考 - www.soinside.com...

bounty到期在6天内。该问题的答案有资格获得+ 50声望赏金。Carlos Diego希望引起更多关注对此问题：我需要使用分水岭来执行此任务，所以请有人可以帮助我更新此代码。

我正在开发一个用于检测病变区域的应用程序，为此，我正在使用抓取来检测ROI并从图像中删除背景。但是，在某些图像中，它不能很好地工作。他最终没有很好地确定感兴趣区域的边界。分水岭可以更好地识别此类工作的边缘，但是，我很难从抓斗过渡到分水岭。在处理抓取图像之前，用户使用touchevent在感兴趣的图像(伤口区域)周围标记一个矩形，以方便算法的工作。如下图所示。

但是，使用其他伤口图像，分割效果不好，显示了ROI检测的缺陷。

[在应用中使用抓取图像

使用桌面中的分水岭的图像

这是代码：private fun extractForegroundFromBackground(coordinates: Coordinates, currentPhotoPath: String): String {

// TODO: Provide complex object that has both path and extension

// Matrices that OpenCV will be using internally

val gray_mat = Mat()

val threeChannel = Mat()

val srcImage = Imgcodecs.imread(currentPhotoPath)

val iterations = 5

Imgproc.cvtColor(srcImage, gray_mat, Imgproc.COLOR_RGBA2RGB)

Imgproc.cvtColor(srcImage, threeChannel, Imgproc.COLOR_RGB2GRAY)

Imgproc.threshold(threeChannel, threeChannel, 0.0, 255.0, Imgproc.THRESH_OTSU)

val fg = Mat(srcImage.size(), CvType.CV_8U)

Imgproc.erode(threeChannel, fg, Mat(), Point(-1.0, -1.0), 2)

val bg = Mat(srcImage.size(), CvType.CV_8U)

Imgproc.dilate(threeChannel, bg, Mat(), Point(-1.0, -1.0), 3)

Imgproc.threshold(bg, bg, 1.0, 128.0, Imgproc.THRESH_BINARY_INV)

val firstMask = Mat(srcImage.size(), CvType.CV_8U, Scalar(0.0))

val marker_tempo = Mat()

firstMask.convertTo(marker_tempo, CvType.CV_32S)

Imgproc.watershed(srcImage, marker_tempo)

marker_tempo.convertTo(firstMask, CvType.CV_8U)

// Mask image where we specify which areas are background, foreground or probable background/foreground

//val firstMask = Mat()

val source = Mat(1, 1, CvType.CV_8U, Scalar(Imgproc.GC_PR_FGD.toDouble()))

val rect = Rect(coordinates.first, coordinates.second)

// Run the grab cut algorithm with a rectangle (for subsequent iterations with touch-up strokes,

// flag should be Imgproc.GC_INIT_WITH_MASK)

Imgproc.grabCut(srcImage, firstMask, rect, bg, fg, iterations, Imgproc.GC_INIT_WITH_RECT)

// Create a matrix of 0s and 1s, indicating whether individual pixels are equal

// or different between "firstMask" and "source" objects

// Result is stored back to "firstMask"

Core.compare(firstMask, source, firstMask, Core.CMP_EQ)

// Create a matrix to represent the foreground, filled with white color

val foreground = Mat(srcImage.size(), CvType.CV_8UC3, Scalar(255.0, 255.0, 255.0))

// Copy the foreground matrix to the first mask

srcImage.copyTo(foreground, firstMask)

// Create a red color

val color = Scalar(255.0, 0.0, 0.0, 255.0)

// Draw a rectangle using the coordinates of the bounding box that surrounds the foreground

Imgproc.rectangle(srcImage, coordinates.first, coordinates.second, color)

// Create a new matrix to represent the background, filled with black color

val background = Mat(srcImage.size(), CvType.CV_8UC3, Scalar(0.0, 0.0, 0.0))

val mask = Mat(foreground.size(), CvType.CV_8UC1, Scalar(255.0, 255.0, 255.0))

// Convert the foreground's color space from BGR to gray scale

Imgproc.cvtColor(foreground, mask, Imgproc.COLOR_BGR2GRAY)

// Separate out regions of the mask by comparing the pixel intensity with respect to a threshold value

Imgproc.threshold(mask, mask, 254.0, 255.0, Imgproc.THRESH_BINARY_INV)

// Create a matrix to hold the final image

val dst = Mat()

// copy the background matrix onto the matrix that represents the final result

background.copyTo(dst)

val vals = Mat(1, 1, CvType.CV_8UC3, Scalar(0.0))

// Replace all 0 values in the background matrix given the foreground mask

background.setTo(vals, mask)

// Add the sum of the background and foreground matrices by applying the mask

Core.add(background, foreground, dst, mask)

// Save the final image to storage

Imgcodecs.imwrite(currentPhotoPath + "_tmp.png", dst)

// Clean up used resources

firstMask.release()

source.release()

bg.release()

fg.release()

vals.release()

dst.release()

return currentPhotoPath

}

如何更新代码以使用分水岭而不是抓取？