I am new to programming in trying to make a simple text based video game. my first goal was to make an introduction which was just me coding input ('...') after input to make a short intro / plot overview
![enter image description here][1]
Related
UseCase: I'm trying to extract certain parts of a screenshot which is taken from a game (with a tf object detection model) and extract the text within this part (custom model for the font used in the game).
I have trained a custom model based on SSD Mobilenet V2 and the object detection works quite okish, but sometimes the bounding box is off. I googled about selecting the right images and the right amount for training the custom model, but I couldn't find a good hint in the right direction.
I try to extract the following (surrounded by red):
The environmen can change:
Resolution of the game can be different (1920x1080, WHQD etc.)
Text in the box is not always the same
I have trained with 120 self made images (1920x1080) (90% for training 10% for test) (all of these images where a screenshot of the game) and as I mentioned the results are okish. Sometimes the detected area is off (cutting the content of the box or including a lot area of the box surroundings).
Maybe someone can help me/answering the following questions:
Could a bigger training dataset increase the accuracy?
Should I also take different resolutions into account when creating the training data?
Would it make sense to feed only the boxes without the rest of the game screenshot into the training? Or should I mix screenshots of the whole game and only box screenshots?
Thank you in advance ! :)
I have looked all over the internet to get a way to extract image of everyframe of a video using react-native-ffmpeg. I am making a mobile app and I want to show all per frame images on the video timeline. I want to do this natively on mobile so that I can utilise hardware power of mobile. That is the reason I am looking for react-native-ffmpeg kind of library. Am I in the right direction? This npmjs.com/package/react-native-ffmpeg is what I am trying to use. I need to know the command to do the job.
To calculate frame rate of the video follow this link :
https://askubuntu.com/questions/110264/how-to-find-frames-per-second-of-any-video-file
After finding the frame rate, you can extract each frame now, for example :
To extract all frames from a 24 fps movie using ffmpeg :
The %03d dictates that the ordinal number of each output image will be formatted using 3 digits.
ffmpeg -i input.mov -r 24/1 out%03d.jpg
another resource :
https://gist.github.com/loretoparisi/a9277b2eb4425809066c380fed395ab3
also refer to .execute() method in react-native-ffmpeg.
Is there a way to get coordinates from an form field on an image (scanned image), by using Google vision?
With the (LocalizedObjectAnnotation) can Google detect only objects and creatures
Google OCR (fullTextAnnotation) detects only text
Scenario:
I got an scanned formular. From this scan i would get all form field-positions (input-fields).
It don't work with one or both google method's "LocalizedObjectAnnotation" and "fullTextAnnotation". Because one detect only objects / creatures and the other one only text. So both can't find the input-field in the image.
Has anyone an idee how i get the coordinates for the input-fields?
I am working on webcam and i capture video using v4l2 library but today i found new code for capture video which is using "libv4l2.h" and "libv4lconvert.h". I found that code working in another pixel format which my webcam dose not support. I found some new predefined functions in that code like v4lconvert_create(), v4lconvert_convert() but dose not found any description of there predefined description. so i want description of these function. Please share decsription or any document for these functions.
For example, given File:Wikipedia-logo-v2.svg as input, the output would include:
http://upload.wikimedia.org/wikipedia/en/thumb/8/80/Wikipedia-logo-v2.svg/200px-Wikipedia-logo-v2.svg.png
http://upload.wikimedia.org/wikipedia/en/thumb/8/80/Wikipedia-logo-v2.svg/500px-Wikipedia-logo-v2.svg.png
...
The original image is a vector, the urls you have provided link to the wikipedia thumbnail generator.
It will generate an image of any resolution you specify, you can just change the value in the url and it will generate an image of that size.
I don't know why you would want to use it however. You should just get the original image and scale it yourself to your own needs.