Questions tagged [object-recognition]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
34
votes
2answers
45k views

How to calculate mAP for detection task for the PASCAL VOC Challenge?

How to calculate the mAP (mean Average Precision) for the detection task for the Pascal VOC leaderboards? There said - at page 11: Average Precision (AP). For the VOC2007 challenge, the interpolated ...
14
votes
5answers
2k views

How can you include information not present in an image for neural networks?

I am training a CNN to identify objects in images (one label per image). However, I have additional information about these images that cannot be retrieved by looking at the image itself. In more ...
10
votes
2answers
15k views

How does the bounding box regressor work in Fast R-CNN?

In the fast R-CNN paper (https://arxiv.org/abs/1504.08083) by Ross Girshick, the bounding box parameters are continuous variables. These values are predicted using regression method. Unlike other ...
9
votes
5answers
5k views

How does deep learning helps in detecting multiple objects in single image?

Let's say there are two cars in an image. How can it detect these cars, given that it can detect single car in an image?
8
votes
2answers
7k views

Train object detection without annotated data/bounding boxes

From what I can see most object detection NNs (Fast(er) R-CNN, YOLO etc) are trained on data including ...
8
votes
1answer
7k views

Recognition human in images through HOG descriptor and SVM classifier performs poorly

I'm using a HOG descriptor, coupled with a SVM classifier, to recognise humans in pictures. I'm using the Python wrappers for OpenCV. I've used the excellent tutorial at pymagesearch, which explains ...
7
votes
1answer
3k views

algorithmic difference between image analysis and video analysis

Is there algorithmic difference between analyzing video and an image, say for example,if I want object recognition? Or do I just have to analyze every frame of the the video just as an image? Example,...
7
votes
1answer
3k views

How does YOLO algorithm detect objects if the grid size is way smaller than the object in the test image?

In YOLO algorithm how do these grids output a prediction if some grids only see a small black portion of the car if the model was trained on datasets with full images?
6
votes
0answers
2k views

Python : Feature Matching + Homography to find Multiple Objects

I'm trying to use OpenCV via Python to find multiple objects in a train image and match it with the key points detected from a query image. For my case, I'm trying to detect the tennis courts in the ...
4
votes
1answer
8k views

What techniques to use for image matching

I have a database with around 30,000 pictures. All of them are a different object. They are all from a certain perspective, the pictures itself are the same size but the objects vary in size. I want ...
4
votes
2answers
3k views

Does resizing images during training affect the bounding box annotations?

I am using the TensorFlow object detection API to train my own custom dataset and am preparing annotations for the same. I see from the config file of my pre-trained SSD inception net, the size of the ...
3
votes
1answer
160 views

Object Detection classification

I am currently training a classifier for detecting resistors using TensorFlow Object Detection API. For that, I downloaded resistor images from ImageNet and I am currently labeling those who will be ...
3
votes
2answers
4k views

Bounding Boxes in YOLO Model

The YOLO model splits the image into smaller boxes and each box is responsible for predicting 5 bounding boxes. My question is how does the model make these bounding boxes for every grid cell ? Does ...
3
votes
1answer
3k views

Grouping similar data/images

I'm using CNN, RNN and OpenCV to identify people and cars within images, once I identify several images I'm cropping them and dividing them in cars and people. I would like to group all same-looking ...
3
votes
1answer
99 views

What are the possible ways to handle class unbalance in a large scale image recognition problem with Deep Neural Nets?

I have 22 classes of objects but they have very skewed distributions where max class has 100.000 images and the min class has 1600 images. In that setting I would like to hear some possible solutions ...
3
votes
0answers
39 views

Why is a general/original softmax loss not preferred in FR (face recognition)?

In some papers I've read that softmax loss is not preferred in FR since it does not give a good inter-class and intra-class margins, but could not understand 'why?'. So can someone explain, why ...
3
votes
0answers
259 views

How does region proposal network (RPN) and R-CNN works?

I would like to know where I could find useful articles/papers about the basic concepts of RPN and R-CNN.
3
votes
0answers
107 views

Is it common to preprocess image data before sending it through a deep net? [duplicate]

I'm curious as how convolutional neural network are used in practice for object recognition. Is it common to perform data preprocessing before providing the data to the input layer ? If so, what types ...
2
votes
1answer
218 views

Generic strategy for object detection

I have a huge collection of objects from which only a tiny fraction are in a class of interest. The collection is initially unlabelled, but labels can be added using an expensive operation (for ...
2
votes
1answer
132 views

Object Recognition for classification, is it being used in industry?

I'm wondering if e-commerce companies where products are offered by users, such as EBay, are using Object Recognition to ensure that an uploaded image corresponds to an specific type of object (...
2
votes
1answer
2k views

How to generate Anchor boxes for SSD?

I am currently trying to understand the method of generating anchor boxes for object detection. I am looking at a code where the author has done this task in a very flexible way. But I am having ...
2
votes
1answer
148 views

What does it mean if performance of two different iterations of the same network (CNN model) varies a lot?

So I trained CNN model for people detection on caltech-pedestrian dataset: Then I was curious and evaluated the model in every 1000th iteration on Evaluation toolbox(I guarantee, there is no bug in ...
1
vote
3answers
683 views

Using non-negative matrix factorization (NMF) for facial recognition

I'm interested to find out how to implement NMF for facial recognition. I understand that the NMF works by taking V, which is a matrix of face images (n resolution x m persons), and factorize V = WH, ...
1
vote
1answer
101 views

optical chemical structure recognition from images

I want to recognize name of the chemical structure from the image of chemical structure, like in the given image it is benzene structure I want to recognize that it is benzene from the image(I should ...
1
vote
1answer
24 views

Similar objects same labels

Example: red paprica and green paprica. The output I need is just paprica, should i label them the same or give them two labels "green paprica" and "red paprica" and leater on just treat them as one? ...
1
vote
1answer
70 views

Is there something like class-based object detection? Or class-based selective search?

I've been reading a lot about computer vision lately, and while there is a huge amount of info about object classification, and a lot less on object detection, I have not found anything on class-based ...
1
vote
1answer
89 views

In CNN (Convolutional Neural Network), does the combination of previous layer's filters make next layer's filters?

I know that the first layer uses a low-level filter to see the edge information. As the layer gets deeper, it will represent high-level (abstract) information. Is it because the combinations of ...
1
vote
1answer
161 views

Faster R-CNN: Labels regarding the positive anchors when there are many classes

The authors of the original paper of Faster R-CNN when they refer to the positive anchors, they are labeled as 1. I guess they refer in binary classification. What happens in the case in a task we ...
1
vote
2answers
84 views

what could it be a good descriptor for simple greyscale symbols?

I need to find a good method to extract key points from drawing symbols like elements in CAD drawings (eg in 2D objects for the bathroom that can be placed on a floor plan). I've already tried all ...
1
vote
1answer
716 views

Face Recognition using Eigenfaces and SVM

I am new to machine learning. I want to develop a face recognition system using scikit-learn. This is the example given in the tutorials of scikit-learn. I am not getting how the input is being ...
1
vote
1answer
435 views

Artificial neural network on ternary content addressable memory

One of the applications of Ternary content addressable memory(TCAM) is artificial neural network. How does TCAM do prediction or recognition? How TCAM is related to artificial neural network?
1
vote
0answers
20 views

Pre trained vehicle detection from low altitude view

I have a very noob question. I need some solution to detect all vehicles in the video (or at least in the image). I have tried YOLOv3, however, it cannot recognize cars from the top (like that in the ...
1
vote
0answers
17 views

Using context to improve object detection and image classification

we are building an image classifier using the Tensorflow Object Detection API. Our images often appear in groups, e.g. a cluster of dogs playing in the grass. Ofter our model will recognize some of ...
1
vote
0answers
306 views

YOLO v3 complete architecture

I am attempting to implement YOLO v3 in Tensorflow-Keras from scratch, with the aim of training my own model on a custom dataset. By that, I mean without using pretrained weights. I have gone through ...
1
vote
0answers
30 views

How to prepare photo data for training model to recognize bowling ball name, brand and manufacturer from photo of bowling ball?

I am asked to do this. The client can only prepare a only one photo for each ball from the product page of bowling manufacturer. However, I need huge amount of image data for each ball. Here is ...
1
vote
0answers
87 views

Add training data to YOLO post-training

I've been playing around with YOLOv3 and obtaining some good results on the ~20 custom classes I trained. However, one or two classes look like they can use some additional training data (not a lot, ...
1
vote
0answers
40 views

Detecting directions using Convolutional neural networks [closed]

I am working on a task where I have to detect damages on the vehicles and exactly where the damage has occurred. So I have to not only detect the damage on the door but also mentioned which door(front ...
1
vote
0answers
672 views

What are the model configuration parameters in tensorflow object detection API?

In the Config file there are some parameters which I don't understand properly . I will mention them here. first_stage_features_stride - Is this the ration of input/output ? height_stride (In the ...
1
vote
0answers
561 views

Human face attractiveness estimation

Needed for dating portal. I currently use OpenFace to extract features with DNN. (I don't know whether they have a usable meaning) Then compare them to some model faces' features using euclidian ...
0
votes
1answer
1k views

Pre trained vehicle detection network

I'm looking for a pre-trained net recognizing vehicles, something like the Inception network for images. If that is impossible to find which vehicle detection algorithm would you suggest, possibly ...
0
votes
1answer
3k views

Objects Localization Through CNN

I am new to deep learning and tensor flow and I am trying to train a CNN at localizing digits in the Street View House Numbers data set. To this end I have an input set of 32x32 images and, since I ...
0
votes
1answer
24 views

Uniform detection: a starting point?

Given an image of a worker, I need to verify if he/she is wearing the company's uniform. I tried to Google, but either the search results are about uniform sampling or some object detection tutorials. ...
0
votes
1answer
20 views

Estimate the location of an object in a field using computer vision and math

I'm trying to see how to detect the location of a soccer ball in the field using the live camera. What are some ways to achieve this? At this point I'm more interested in ideas and thoughts and not ...
0
votes
1answer
290 views

why we have run make.sh file initially in darknet and YOLO object detection?

In have seen a couple of text and objection detection algorithm wher the first step everyone dose is to install cython and run a make.sh file . why we have run make.sh file initially in darknet/YOLO ...
0
votes
1answer
27 views

Recommendations to generate a training set of images

We are about to start a series of experiments in physics which will generate 8.5 thousands of images per month. This is a study on microscopic material reactions so the images are not 'normal' objects ...
0
votes
1answer
780 views

mean average precision - pseudo code

There are many blog posts and threads concerning the computation of mAP, both for PASCAL and for COCO. Still, they do not answer some fundamental questions. I am listing here the flow as I understand ...
0
votes
1answer
290 views

Tensorflow Object Detection API

Looking at the Tensor-flow object detection API, and walking through the "How to train your own Object Detector" for raccoons, which is a handy guide to get you up and running. What I would like to ...
0
votes
1answer
330 views

Why is video classification still not that accurate?

I was wondering, with the advent of deep learning, many tasks related to images have been solved to near human accuracy such as classification, object detection etc., however in videos, traditional ...
0
votes
1answer
63 views

Classification with two 1-NN classifiers

I have two images, let's say old and new. In the old one there are 1:M objects, in the new one 1:N. I need to label the objects in the new one based on some metric (yes, I realize object tracking is a ...
0
votes
0answers
27 views

Extract features using Bounding Box

I have a ground truth bounding box for a 3d object. I would like to extract useful features for the object. My goal is to concatenate these visual object features with language features (from the ...