I'm working on an AndroidApp with TensorFlow Lite to process semantic segmentation.
https://www.tensorflow.org/lite/api_docs/java/org/tensorflow/lite/InterpreterApi
Also I'm using U2net model and processing images which are already masked like below.
enter image description here
Problem is masked area could be circle or elliptical shape, so it can't be done with normal process.
Throwing this image into interpreter results in getting just same image in which circle area is white color.
So I have to cut out the circle and throw it, but only the circle area is included.
Throwing cut-out image does't work, because it's out of shape.
The arrays must be square just like normal images.
I counld't find any lead to solve this problem.
Any advice would be appriciated.
Thank you.
Related
i've created over 1200 images with labels for yolo detection and the problem is every image size is 800x600 and all the objects with labels are in the middle of the image. so i wanna crop the rest of the part since objects are placed in the middle.
so the size of images would be something like 400x300 (crop left, right, top, bottom equally) but the objects will still be in the middle. but how do you convert or change the coordinates other than labeling all over again?
# (used labelimg for yolo)
0 0.545000 0.722500 0.042500 0.091667
1 0.518750 0.762500 0.097500 0.271667
heres one of my label .txt. sorry for my bad english!
I'm trying to collect my own training data set for the image detection (Recognition, yet). Right now, I have 4 classes and 750 images for each. Each images are just regular images of the each classes; however, some of images are blur or contain outside objects such as, different background or other factors (but nothing distinguishable stuff). Using that training data set, image recognition is really bad.
My question is,
1. Does the training image set needs to contain the object in various background/setting/environment (I believe not...)?
2. Lets just say training worked fairly accurately and I want to know the location of the object on the image. I figure there is no way I can find the location just using the image recognition, so if I use the bounding box, how/where in the code can I see the location of the bounding box?
Thank you in advance!
It is difficult to know in advance what features your programm will learn for each class. But then again, if your unseen images will be in the same background, the background will play no role. I would suggest data augmentation in training; randomly color distortion, random flipping, random cropping.
You can't see in the code where the bounding box is. You have to label/annotate them yourself first in your collected data, using a tool as LabelMe for example. Then comes learning the object detector.
I've been searching around the web about how to do this and I know that it needs to be done with OpenCV. The problem is that all the tutorials and examples that I find are for separated shapes detection or template matching.
What I need is a way to detect the contents between 3 circles (which can be a photo or something else). From what I searched, its not to difficult to find the circles with the camera using contours but, how do I extract what is between them? The circles work like a pattern on the image to grab what is "inside the pattern".
Do I need to use the contours of each circle and measure the distance between them to grab my contents? If so, what if the image is a bit rotated/distorted on the camera?
I'm using Xamarin.iOS for this but from what I already saw, I believe I need to go native for this and any Objective C example is welcome too.
EDIT
Imagining that the image captured by the camera is this:
What I want is to match the 3 circles and get the following part of the image as result:
Since the images come from the camera, they can be rotated or scaled up/down.
The warpAffine function will let you map the desired area of the source image to a destination image, performing cropping, rotation and scaling in a single go.
Talking about rotation and scaling seem to indicate that you want to extract a rectangle of a given aspect ratio, hence perform a similarity transform. To define such a transform, three points are too much, two suffice. The construction of the affine matrix is a little tricky.
USPTO requires patent drawings to be black and white lines images.
I'm using blender to make 3D models. At first I got this:
The problem is it's grayscale with no black lines.There's a answer to suggest using toon shader. Convert 3D models to patent digrams
I checked "Edge" and set "Threshold" to max 255 in "Render" tab, I got:
It's getting better but need more edges to be drawn. I searched and found a tutorial http://www.minimaexpresion.es/?p=1070&lang=en , then I got:
It's too complicated for me and I don't know how to use render layers. So I tried another tutorial http://download.blender.org/documentation/oldsite/oldsite.blender3d.org/80_Blender%20tutorial%20Toon%20Shading.html , which says I should assign different materials with different colors to different objects, so I tried and got this:
It leaves only one way to give a shot: render layers. Is there any simple methods to make it work? I only want this and convert it to indexed colors with black and white palette:
And the "Freestyle" only has one option about line thickness:
You were close in the second image. Instead of using the Edge postprocessor, look in the Render panel check the box labelled "Freestyle".
Then in the Render Layers panel there will be a list of configurable options for Freestyle, including how thick you want the lines and the minimum angle required to render an edge.
The best results are if you use mostly shadeless materials with simple textures (just solid colour).
I was wondering if anyone knows of an algorithm to retrieve shapes from an edge detection filter.
I basically want process an image and find all the shapes in the image then fill them with rectangles using greedy fill. Though I have not found an algorithm that will help me create the shapes from edge detection.
Cam anyone point me in the right direction?