1,341 questions
0
votes
0
answers
63
views
Google Cloud Vision API Web Detection - Missing Image URLs
I'm using the Google Cloud Vision API's Web Detection feature, but I'm encountering an issue where the image URLs (fullMatchingImages, partialMatchingImages, visuallySimilarImages) are not being ...
- 1
0
votes
1
answer
63
views
Image denoising of a grey background with black spots [closed]
How can I highlight the black spots in the image below for detection?
I've tried a lot of things, gaussian filter, change of contrast, contour filters... but nothing really worked. Currently, I'm ...
- 11
0
votes
0
answers
281
views
How to Integrate Google Cloud Vision API with PHP for Image Label Detection?
I am trying to integrate the Google Cloud Vision API into my PHP project to perform image label detection. I've followed the official documentation, but I'm running into some issues. Here are the ...
0
votes
1
answer
121
views
Python tesseract OCR detecting text improperly
testimg.png:
I am trying to detect the Text in this image and it gives me nothing, it works for some other text barely. It gives me some of the word replaced with random letters and i have to compare ...
- 11
0
votes
0
answers
77
views
Grid Image Recognition for Board Game
I want to create an automatic scoring app for a board game. The hard part of the app would be to turn this image into a data structure:
[
[
{ name: "granary" },
{ name: "opposite ...
- 49
2
votes
3
answers
591
views
Stable icon recognition by opencv python
I have the following issue: I need to detect icons in an image reliably. The image also contains text, and the icons come in various sizes.
Currently, I'm using Python with the cv2 library for this ...
0
votes
1
answer
24
views
Which algorithm to use to detect the appearance of sidebar on car multimedia booting?
I need to create a system for detecting the time that elapses between the start of booting the multimedia system in the car until the first appearance of the sidebar on the screen. Sidebar has a ...
0
votes
0
answers
49
views
Hough Intersection points
I made a hough transform for car plate recognition. I found some vertical and horizontal lines. I need to make an algorithm such that it will choose the right rectangle shape.
I tried to control it ...
- 1
0
votes
0
answers
39
views
Optimal autoencoder model for picture anomaly detection
I'm training an autoencoder to detect anomalies among pictures based on the decoder error value. I tried out different ways of image preprocessing, NN architectures, losses, activation functions, ...
- 1
0
votes
0
answers
33
views
Figures detection in a picture using ML.NET
How can I use ML.NET services to detect different figures inside a picture? For example, detecting squares, circles, triangles, etc. At the end of the process, I should receive a solution like:
Number ...
1
vote
1
answer
266
views
How can I use Google Document AI OCR to find the non-text images in a text document?
How can I use Google Document AI OCR to find the non-text images in a text document?
I'm using Google Document AI Enterprise OCR to OCR images (scans of old books_, and it works well. The books have ...
- 9,139
0
votes
0
answers
72
views
How to Read the text from images(OCR) where the font style is 7 segment font
I have been working on extracting text from images, specifically focusing on seven-segment fonts, using .NET. Unfortunately, my attempts with popular libraries like Tesseract, IronOcr and many more ...
0
votes
1
answer
284
views
How crop image before Image Classification
I am using MediaPipe to find the breed of a dog, if there is one, in a camera image. I first use ObjectDetector, and if it finds a dog, I send what is inside the bounding box to ImageClassifier, with ...
- 171
0
votes
1
answer
85
views
How can i fix colour detection in my code?
import pyautogui
import keyboard
import time
running = True
print("Script will start in 5 seconds.")
time.sleep(5) # Wait for 5 seconds before starting
while running:
keyboard....
- 1
0
votes
0
answers
36
views
Clarifai custom model
I'm trained a custom model for image recognition and it works well along with response of the concept and value i tried to get the custom meta data which i added to the concepts but unable to get the ...
- 1
0
votes
1
answer
301
views
Extracting Color Information from a Trained CNN Model
I am currently working on interpreting a trained CNN model used for image recognition. Specifically, I want to understand how color information is represented in the feature vector, particularly in ...
1
vote
0
answers
81
views
How to extract the line segment information in a picture accurately in Python
I'm trying to get detailed information on each line segment, such as the coordinates of two endpoints and whether it is straight or curved, in a picture in Python.
For example, an input image below is ...
- 11
1
vote
1
answer
103
views
How can I fill missing parts in particle borders, so that these borders/contours form a continous outline?
I have this binary Black Particle Borders image of many non-spherical particle borders/outlines. Unfortunately, due to bad image quality, the borders are not continuous, but have some gaps. Is there ...
- 11
1
vote
1
answer
261
views
How to find image on screen if there are rapid objects moving over it?
I am currently discovering image recognition and my goal is to get all the informations from the board of a mobile game that look like this :
board
As you can see, there are 5 different dices, their ...
- 13
-1
votes
1
answer
32
views
Program using screenshots on Windows 10 server errors upon SSH disconnection
I have a Python program running on a Windows 10 server hosted online, which locates specific icons using screenshots. The program uses image recognition to identify these icons. However, when I ...
- 11
2
votes
1
answer
882
views
KerasOCR, EasyOCR, Pytesseract not able to recognize simple numbers
I was trying to run OCRs on my single character images, all being numbers. I tried running EasyOCR, Keras-OCR and Pytesseract on the image, but none returned proper output. I even tried MNIST, but ...
- 21
0
votes
1
answer
196
views
Create and display 10-bit images on a 10-bit monitor
As part of a visual recognition experiment, I need to generate 10-bit images pixel-by-pixel and display them on the monitor (10 bits per color). I would like to understand how this can be implemented ...
- 1
-1
votes
1
answer
47
views
how can I improve my traning and validation accuracies? [closed]
I juste trained 3d Resnet50 model on my dataset (I am using the MSR Daily activity 3D which consist of 16 actions and which is relatively a small dataset) and to get better results I traind it using a ...
- 11
1
vote
2
answers
269
views
pyautogui not working on MacOS ('<' not supported between instances of 'str' and 'int')
I`m trying to find an image on the screen using pyautoGUI on MacOS. The code i use is the following:
import pyautogui
img = 'name.png'
img = pyautogui.locateCenterOnScreen(img)
Can anyone help me? ...
2
votes
0
answers
223
views
Getting "Cannot read property 'fetch' of undefined", while loading "@tensorflow-models/coco-ssd"
I'm developing an application in React Native, the primary purpose of which is to select a video from a gallery and run an object detection model on it. I'm currently using a TensorFlow model named &...
0
votes
0
answers
207
views
I get 'ModuleNotFoundError: No module named 'tensorflow.compat'
Here is the code,
from keras.preprocessing import image
from keras.applications.vgg16 import VGG16
from keras.applications.vgg16 import preprocess_input
from keras.models import Model import numpy ...
- 21
0
votes
2
answers
334
views
Automatically find a rectangle and crop image to it in python
So say I have lots of images similar to these ones:
I am trying to get the rectangle with the numbers inside, its the one with the lighter background, also I would like to get rid of those lines but ...
-1
votes
1
answer
2k
views
ReferenceError: Property 'document' doesn't exist
friend. I seeketh thy assistance in recognizing the text from an image. I hath utilized tesseract.js for this purpose. Pray, how may I rectify this matter?
import Tesseract from 'tesseract.js';
const ...
- 13
-1
votes
1
answer
197
views
Cv2 is refusing to use imread and TM_CCOEFF_NORMED when trying to compare 2 images (this is in pycharm, python 3.10.1)
I am trying to make a game where the user submits and image and then that image gets compared to a hard coded template. If the images are close enough then the user wins. I coded this segment about 3 ...
1
vote
1
answer
539
views
TensorFlow Prediction for each image in a folder
I created a model in TF, it recognizes one image, but when I try to make predictions for multiple images in a folder, I get an error.
import tensorflow as tf
import os
import cv2
import imghdr
import ...
- 13
0
votes
1
answer
48
views
Image recognition model prediction always the same for unseen images
I'm working on an image recognition project with a self-created dataset that contains 563 files belonging to 2 classes. I split the dataset into training and validation sets with 395 images in ...
- 21
1
vote
0
answers
30
views
How to improve the digital recognition rate in fuzzy images
I am currently working on some printed numbers on steel plates, using PaddleOCR, but some images are not clear, or the printed numbers themselves are not clear. How can I improve the digital ...
- 11
0
votes
1
answer
56
views
Trouble detecting numbers using pytesseract using a pixeled image
I am trying to detect/read the number in the image below. I apply a mask to the image (also shown below), and come back with a rather pixeled set of numbers. The only method for me to retrieve these ...
- 5
2
votes
1
answer
703
views
Object detection or image classification? Training a model to recognize playing cards
I have been experimenting with object detection recently, using Faster R-CNN and YOLOv7 to train models on pre-existing datasets.
Using a UNO card dataset I quite accurately detected the type of UNO ...
- 21
0
votes
1
answer
33
views
Pytesseract not giving excpected resaults
using pytesseract for image to text along with some basic image enhancing, Problem is that im getting very weird resaults.
Pyton
import cv2
import pytesseract
import numpy as np
from PIL import Image
...
- 3
3
votes
0
answers
610
views
How achieve similar preciseness in Cloud Vision API detection as Google Lens?
I would like to detect different plants via Cloud Vision API. I have previously admired the preciseness of Google Lens when detecting plants, but when I try the same thing via Cloud Vision API, I do ...
- 579
0
votes
1
answer
499
views
| ValueError: Input 0 of layer "sequential" is incompatible with the layer: expected shape=(None, 28, 28), found shape=(None, 28, 3)
import numpy as np
import matplotlib.pyplot as plt
import cv2 as cv
import tensorflow as tf
from tensorflow.keras import datasets, layers, models
fashion_mnist = tf.keras.datasets.fashion_mnist
(...
- 3
1
vote
0
answers
436
views
Canny edge detector, but only for the object I want
I want to detect only the tray edges in this picture. I tried with the Canny edge detector. It detects edges in the whole picture. What can I do to just detect the tray? I used the code here.
I just ...
- 98
0
votes
2
answers
864
views
API to retrieve images from within an image or pdf
I am looking for a way to extract images from within another image. For example:
Here is a picture taken of a paper. It includes text, an image of a camera, and an image of a qr code. Is there an API ...
- 73
1
vote
0
answers
216
views
How do i fix 'Loss is nan, stopping training'?
I've been trying to run an specific proyect (https://github.com/nicolaihaeni/MinneApple) where i have to run a training model for fruit counting/detection with image recognition.
I tried running the ...
0
votes
1
answer
945
views
calculation of Detection, Recognition and Identification (DRI) ranges of a camera for different objects
I want to calculate the DRI ranges of a camera using it's resolution, focal length , sensor pixel pitch and target real size. I have these values but I didn't find any equations to calculate DRI range ...
- 11
0
votes
0
answers
137
views
Object Recognition using Python (OpenCV)
I am trying to implement a program where the user inputs RGB values and the program detects number of objects using OpenCV library. I was able to implement the functionality. However, it works with ...
0
votes
2
answers
762
views
Recognizing black and white images with OpenCV
I have this set of images :
The leftmost one is the reference image.
I want to have a value telling me how close is any of the other images to the leftmost one.
I experimented with matchShapes(), by ...
- 21
0
votes
1
answer
131
views
Can the plotly.io.write_html be used to also plot images?
Usually, we use the line to plot graphs and confusion matrices. However, the official documentation doesn't really specify which types of figures are supported.
Can I actually use it for image files?
(...
- 21
0
votes
2
answers
4k
views
How to convert polygon coordinates to rectangle(yolo format) for an image labelling?
I am trying to read water meter reading through OCR, however, my first step is to find ROI. I found a dataset from Kaggle with the labeled data for the ROI. But they are not in rectangles, rather in a ...
- 147
4
votes
1
answer
589
views
Algorithm for 'pixelated circle' image recognition
Here are three sample images. In these images I want to find:
Coordinates of the those small pixelated partial circles.
Rotation of these circles. These circle have a 'pointy' side. I want to find ...
- 163
0
votes
1
answer
184
views
How to find logos on a website screenshot
I'm looking for a way to check if a given logo appears on a screenshot of a webpage. So basically, I need to be able to find a small predefined image on a larger image that may or may not contain the ...
- 10k
0
votes
0
answers
647
views
How do I compare two images and transform them to match?
I am taking two similar images and putting one on top of the other as semi transparent overlay.
What I'm trying to achieve now is to compare the difference between them and transform (scale, crop, ...
- 635
0
votes
1
answer
597
views
How do I get pyTesseract to only get numbers from an image
I've been trying to make a sudoku solver taking an input of sudoku game in png form.
I've tried to turn the digits in image into numbers so that I can put them on a list and implement an algorithm ...
1
vote
0
answers
539
views
How to get the Intel UHD Graphics 605 i915 videocard working with Vulkan?
i have an Intel UHD Graphics 605 (i915) and i want to use it with Vulkan/ncnn.
The information from this site is, that Vulkan should work with version 1.1.103:
https://technical.city/de/video/UHD-...
- 13