Stack Exchange Network

Stack Exchange network consists of 175 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [image-recognition]

A form of signal processing where the input is an image. Usually treating the digital image as a two-dimensional signal (or multidimensional). This processing may include image restoration and enhancement (in particular, pattern recognition and projection).

0
votes
0answers
6 views

Facial Recognition Using One shot Learning Research Paper

1) I am looking for a latest Research Paper for "Facial Recognition Using One shot Learning" for my semester Project. I want to implement that paper and want to improve that. i have searched on ...
1
vote
0answers
7 views

How do I interpret the Wavelet scattering transform frequency plane and tree diagrams?

I've been reading through this paper on "Invariant Scattering Convolution Networks" and am having a difficult time interpreting the tree diagrams and frequency plane diagrams shown respectively below. ...
1
vote
1answer
31 views

How can on quickly look up people from a large database?

Vocabulary Face detection: Finding all faces in an image. Face representation: The simplest way to represent a face is as an image (pixels / color values). This is not very space efficient and likely ...
0
votes
1answer
15 views

How to encode a time series as an image to feed it into CNN?

I want to try CNN in the task of stock chart pattern recognition. I suspect that feeding a line chart won't work because the image will have a lot of empty pixels. What time series encoding options ...
0
votes
0answers
28 views

Is it possible to make a 'forked path' neural network?

I want to make a network, specifically a CNN for image recognition, that takes an input, processes it the same way for several layers, and then at some point splits before coming to two different ...
1
vote
1answer
49 views

YOLO: What is better? multiple networks per label or multiple labels in single network?

I would like to use a YOLOv3 network,load in the preexisting trained weights, then retrain the ending layer to recognize say, 20 labels. Would adding labels to a single network in training reduce its ...
1
vote
2answers
60 views

What is the difference between “offline trained model” and “pretrained model”?

I am confused that both are same or not, and then how can I differentiate with the online training model.
4
votes
1answer
78 views

getting the weights of intermediate layer in keras

I have an image dataset 376 classes each class has 15 pictures corresponds to a person. I would like to get the feature vector that corresponds to each person. What I have done is, after I compiled ...
0
votes
0answers
21 views

Optimisation of Image classifier CNN

I built a convolutional neutral network, now I want to optimise the model using genetic algorithm and Bat algorithm. How should I do it? I am using following packages in code: tensorflow numpy tflearn ...
1
vote
0answers
13 views

Learning image embddings for clustering based on custom distance metric

I have a large dataset of images, and i can calculate their distance to oneanother. I will at a later point recieve new images where i can not determine their distances to the ones in my training set(...
1
vote
0answers
21 views

How can I detect partially obscured objects using Python?

I'm building a computer vision application using Python (OpenCV, keras-retinanet, tensorflow) which requires detecting an object and then counting how many objects are behind that front object. So, ...
4
votes
1answer
43 views

Image Matching for similar products

Is it technically possible to find out similar products online based on an given image? Say the first link is a hoodie for women selling on Amazon. I want to do two things. Based on the image, I ...
1
vote
0answers
17 views

Mask RCNN detecting object but mask is inaccurate

I am trying to detect the inner region of a object. Currently I am using the mask rcnn implementation provided by tensorflow in the models zoo. The object is similar to a hula hoop that is square in ...
0
votes
0answers
16 views

Encoder Decoder Network Image Compression

Could you train an encoder decoder network to take an image in and attempt to recreate that image as an output. I am basically interested at looking at the intermediate feature vector representation ...
0
votes
0answers
15 views

Matching a book spine image against a database of images

I am working on a problem related to book identification in a library. For this I have to match a book spine image (query image) against a database of book spines and find the best match so that I can ...
2
votes
3answers
41 views

Image Classification on non real images

I was wondering how image classifier networks perform on images that are not photographs. For example if you were to feed a drawing of a car or a face to an image classifier that was only trained on ...
1
vote
0answers
36 views

Image preprocessing: How to resize / align / cut images of various sizes?

I want to create a new dataset for image recognition. If I have Object A that I want to recognize in images, and multiple images of various different sizes, how do I preprocess them so that they ...
2
votes
2answers
66 views

CNN strategy in recognizing spinned images

I wrote my CNN code from scratch with some convolution kernels. But my CNN can't recognize flipped/spinned images correctly when there are only a few convolution kernels (3*3). My convolution kernels ...
1
vote
0answers
28 views

How to filter out babies from image dataset

I'm trying to perform a large image dataset clean up (filtering all the minors\babies from it). My initial approach was to utilize age detector, such as https://github.com/deepinsight/insightface/...
2
votes
2answers
69 views

How can I train a model for localizing objects(classification not required) in Python

I need to make a model that creates bounding box around objects(but does not classify them) for a competition. Which libraries or pre-trained models should I use. I need values of x1,x2(x1+w),y1,y2(y1+...
0
votes
0answers
21 views

Implementation of Siamese network

What would be the ideal ratio of positive, negative image pairs, and the number of image pairs to classify if two images are of same person in Siamese network ?
1
vote
3answers
51 views

Where/How to start? [closed]

I want to create an application that recognises diseases from images, I know this require databases of images and image segmentation but where do I start? What should I start learning? I know nothing ...
0
votes
1answer
15 views

Useful metrics to compare network-output image to true image?

I'm designing a supervised network that would require to output an image. I'm wondering what are the best metrics to find similarity between the output and actual target image. So far, my best ...
0
votes
0answers
16 views

Recognition of objects in almost plain background

I want to recognize climbing holds in a climbing wall. I thought about implementing my own heuristic algorithm for background detection because it's almost plain, but I was wondering if this kind of ...
1
vote
0answers
204 views

“10-year-challenge” data for age algorithms? [closed]

Both on FB and IG, I see people posting themselves before 10y and now. I have no idea how this challenge started. Could it be a way to collect a colossal amount of data, that could be used to train ...
0
votes
0answers
11 views

image caption generator

I see two models of image caption generator online: In the above model, the first LSTM cell of decoder takes the entire image as an input. In the above model, all the LSTM cells of the decoder take ...
0
votes
1answer
18 views

Given a 12x12 binary image (only black and white pixels) what is its dimensionality? And how can I define dimensionality of a data space?

Suppose I have a grid 12x12 of pixels that can be only black or white. I can't understand if the dimensionality is 2 or 3. I mean... Is dimension given by 12x12 or 12x12x2 ?
0
votes
1answer
34 views

What is a suitable Tensorflow model to classify images into foggy/not foggy?

I want to classify photos taken by multiple webcams that are operating in mountainous regions into foggy / not foggy. The photos are in various sizes and were taken under very different light ...
0
votes
1answer
13 views

Sobel Operator || Pixel Constraint

I am trying out the Sobel vertical operator to identify vertical edges in a picture. In each image there is one rectangle but the difference is that in 1 image the 2 vertical lines in the rectangle is ...
0
votes
1answer
22 views

Face embedding of unseen images

I've read about FaceNet but the main problem is still unclear for me. Does embedding work on the trained images only? Or once trained on a big dataset it will readily cluster unknown faces without re-...
1
vote
0answers
740 views

i got the following error : 'numpy.ndarray' object has no attribute 'detectMultiScale' to show image in python?

import cv2 videoCam = cv2.VideoCapture(0) face = cv2.CascadeClassifier('haarcascade_frontalface_default.xml') eye = cv2.CascadeClassifier('haarcascade_eye.xml') nose = cv2.CascadeClassifier('...
0
votes
1answer
17 views

Is it possible to train this image classifier?

I'm writing a mobile app that will enable a user to scan a Craft Beer Label from a bottle, tap, six pack, etc. The scan will only work for my customers who are the Brewers themselves, so I will have ...
2
votes
2answers
570 views

How to transform a folder of images in a csv file

I have a folder with a lot of images that I want to use to bild a classificator using a SVM model in python with sklearn. I've always used csv file as train/test set with sklearn, how can I make it? (...
1
vote
2answers
78 views

Counting non-overlapping objects in a semantic segmentation prediction mask

What is a good way to count the number of roofs detected by a CNN in the following output on the right (produced using keras/tensorflow): I need to count the discrete shaded areas and estimate their ...
1
vote
0answers
14 views

Generating labeled dataset for training a neural network

I am currently working on a project in which i'm supposed to classify whether an image contains a translucent watermark or not. This is hard to do with standard object classification or template ...
1
vote
2answers
71 views

When using Data augmentation is it ok to validate only with the original images?

I'm working on a multi-classification deep learning algorithm and I was getting big over-fitting: My model is supposed to classify sunglasses on 17 different brands, but I only had around 400 images ...
1
vote
0answers
55 views

Rain radar image noise reduction and cleanup

An application that I am building is plotting rain radar images on map. The images are transparent PNGs that are sourced straight from the local meteorological service. As can be seen in the example, ...
1
vote
0answers
133 views

Using a custom R generator function with fit_generator (Keras, R)

I'd like to train a convolutional network to solve a multi-class, multi-label problem on image data. Due to the nature of the data, and for reasons I'll spare you, it would be best if I could use a ...
1
vote
1answer
21 views

In handwritten digit recognition problem using logistic regression, what changes needed to add another class “Not a Digit”

In handwritten digit recognition problem using logistic regression, normal implementation would forcibly classify even a picture of dog or cat as a digit. To eliminate this, what changes are needed to ...
1
vote
1answer
77 views

Does image resizing lower the prediction accuracy of MLP?

I am implementing a vanilla neural network (MLP) to do image classification in python using tensorflow on images of honey bees to detect their health status. The images in my dataset are of different ...
0
votes
1answer
69 views

Why my model can't recognise my own hand written digit?

Currently i am working on digit recognizer[0-9]. My model train accuracy 100% and test accuracy ...
1
vote
1answer
65 views

image recognition: fully connected network vs CNN

To recognize handwritten digits, I have a fully connected network, containing only 2 layers: input layer (all pixels of the image) and output layer (0 or 1). I use the simplest linear regression for ...
2
votes
1answer
66 views

Does CNN take care of zoom in images?

Suppose a convolution neural network is trained on small images of an object, say flower, as in following 3 training images: Will this CNN correctly classify if the same object is present in zoomed ...
1
vote
1answer
36 views

How can we use machine learning to distnguish between similarly looking images

How can I build a model which can distinguish between Milk and Phenyl? I want to predict whether a given item is edible to eat or not. If I train a model with thousands of photos of Milk and Phenyl ...
1
vote
2answers
1k views

How to properly save and load an intermediate model in Keras?

I'm working with a model that involves 3 stages of 'nesting' of models in Keras. Conceptually the first is a transfer learning CNN model, for example MobileNetV2. (Model 1) This is then wrapped by a ...
4
votes
1answer
227 views

What is difference between intersection over union (IoU) and intersection over bounding box (IoBB)?

Can someone give a detailed explanation IoU and IoBB along with that the differences between them.
2
votes
3answers
512 views

Unbalanced training data for different classes

What precautions do I need to take while trying to develop a CNN for classification of images if there is much more training data for one label. For example: ...
1
vote
0answers
16 views

Magnification factor in image classification

If a CNN is trained on images focusing on an object, will it also recognize when multiple such objects are present in the image? For example can a network trained on single flower images also ...
4
votes
1answer
95 views

Detecting abnormal 'cat' behaviour via Supervised Learning

A few work colleagues and I were looking through a recently replaced 'cat', we had in the workplace. For those of you which are curious, the 'cat' in this context, refers to a specific type of pump ...
0
votes
1answer
28 views

What does the co-ordinate output in the yolo algorithm represent?

My question is similar to this topic. I was watching this lecture on bounding box prediction by Andrew Ng when I started thinking about output of yolo algorithm. Let's consider this example, We use ...