what is the best approach to detect small objects with similar shape?Computer vision: Identifying different items in screenshotData preprocessing: Should we normalise images pixel-wise?Faster-RCNN how anchor work with slider in RPN layer?Retraining an object detection model on fewer classesTattoo Image Recognition - Should I Crop Training Data BackgroundHow is Stochastic Gradient Descent done in Faster RCNN?What is the most efficient method to detect drowsiness?How can I detect partially obscured objects using Python?
Ban on all campaign finance?
How to deal with a cynical class?
What options are left, if Britain cannot decide?
Can elves maintain concentration in a trance?
Did Ender ever learn that he killed Stilson and/or Bonzo?
Instead of Universal Basic Income, why not Universal Basic NEEDS?
Fantasy series where a Vietnam vet is transported to a fantasy land
When do we add an hyphen (-) to a complex adjective word?
What does it mean to make a bootable LiveUSB?
What is a function that separates points of a manifold?
Does splitting a potentially monolithic application into several smaller ones help prevent bugs?
What is IP squat space
Russian cases: A few examples, I'm really confused
Is having access to past exams cheating and, if yes, could it be proven just by a good grade?
Sailing the cryptic seas
Is it normal that my co-workers at a fitness company criticize my food choices?
How could a scammer know the apps on my phone / iTunes account?
Professor being mistaken for a grad student
How do anti-virus programs start at Windows boot?
Why would a flight no longer considered airworthy be redirected like this?
Problems with making formula look great
Should we release the security issues we found in our product as CVE or we can just update those on weekly release notes?
Site Collection Administrator has left the building
Can I get a Visa Waiver after spending 6 months in USA with B-2 Visa?
what is the best approach to detect small objects with similar shape?
Computer vision: Identifying different items in screenshotData preprocessing: Should we normalise images pixel-wise?Faster-RCNN how anchor work with slider in RPN layer?Retraining an object detection model on fewer classesTattoo Image Recognition - Should I Crop Training Data BackgroundHow is Stochastic Gradient Descent done in Faster RCNN?What is the most efficient method to detect drowsiness?How can I detect partially obscured objects using Python?
$begingroup$
I'm working a model which detect different products in supermarket shelf. In the training data, there are a lot of objects with similar shape placed very close to or stacked to each others.(eg: milks with different brands are stacked, placed on the same shelf, the model should be able to detect milk1, milk2). What is the best approach to this problem. I've tried to train a Faster RCNN, but the RPN isn't working well. I've also tried feature matching, but it cannot detect partially visible objects. Any help will be appreciated!
The training images look like this
Link to FRCNN result when detect 2 type of milk and 1 type of yogurt
faster r-cnn detection result
computer-vision object-detection faster-rcnn
asked yesterday
Hoang Dang TuanHoang Dang Tuan
133
New contributor
Hoang Dang Tuan is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
|
show 2 more comments
$begingroup$
I'm working a model which detect different products in supermarket shelf. In the training data, there are a lot of objects with similar shape placed very close to or stacked to each others.(eg: milks with different brands are stacked, placed on the same shelf, the model should be able to detect milk1, milk2). What is the best approach to this problem. I've tried to train a Faster RCNN, but the RPN isn't working well. I've also tried feature matching, but it cannot detect partially visible objects. Any help will be appreciated!
The training images look like this
Link to FRCNN result when detect 2 type of milk and 1 type of yogurt
faster r-cnn detection result
computer-vision object-detection faster-rcnn
asked yesterday
Hoang Dang TuanHoang Dang Tuan
133
New contributor
Hoang Dang Tuan is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
$begingroup$
The text in images is clear? Can't you extract some data from them?
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
I just added some training sample. Would it work better if the input images in higher resolution?
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
Another question, Is the position of the camera is same for objects with same shape and different size?
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
yes, all object are observed in the same distance
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
@alirezazolanvari I just added the link to detection result using faster r-cnn
$endgroup$
– Hoang Dang Tuan
yesterday
|
show 2 more comments
$begingroup$
I'm working a model which detect different products in supermarket shelf. In the training data, there are a lot of objects with similar shape placed very close to or stacked to each others.(eg: milks with different brands are stacked, placed on the same shelf, the model should be able to detect milk1, milk2). What is the best approach to this problem. I've tried to train a Faster RCNN, but the RPN isn't working well. I've also tried feature matching, but it cannot detect partially visible objects. Any help will be appreciated!
The training images look like this
Link to FRCNN result when detect 2 type of milk and 1 type of yogurt
faster r-cnn detection result
computer-vision object-detection faster-rcnn
asked yesterday
Hoang Dang TuanHoang Dang Tuan
133
New contributor
Hoang Dang Tuan is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
I'm working a model which detect different products in supermarket shelf. In the training data, there are a lot of objects with similar shape placed very close to or stacked to each others.(eg: milks with different brands are stacked, placed on the same shelf, the model should be able to detect milk1, milk2). What is the best approach to this problem. I've tried to train a Faster RCNN, but the RPN isn't working well. I've also tried feature matching, but it cannot detect partially visible objects. Any help will be appreciated!
The training images look like this
Link to FRCNN result when detect 2 type of milk and 1 type of yogurt
faster r-cnn detection result
computer-vision object-detection faster-rcnn
computer-vision object-detection faster-rcnn
asked yesterday
Hoang Dang TuanHoang Dang Tuan
133
New contributor
Hoang Dang Tuan is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked yesterday
Hoang Dang TuanHoang Dang Tuan
133
New contributor
Hoang Dang Tuan is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
edited yesterday
Hoang Dang Tuan
asked yesterday
Hoang Dang TuanHoang Dang Tuan
133
New contributor
Hoang Dang Tuan is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked yesterday
Hoang Dang TuanHoang Dang Tuan
133
asked yesterday
Hoang Dang TuanHoang Dang Tuan
133
133
New contributor
Hoang Dang Tuan is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
New contributor
Hoang Dang Tuan is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
Hoang Dang Tuan is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$begingroup$
The text in images is clear? Can't you extract some data from them?
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
I just added some training sample. Would it work better if the input images in higher resolution?
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
Another question, Is the position of the camera is same for objects with same shape and different size?
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
yes, all object are observed in the same distance
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
@alirezazolanvari I just added the link to detection result using faster r-cnn
$endgroup$
– Hoang Dang Tuan
yesterday
|
show 2 more comments
$begingroup$
The text in images is clear? Can't you extract some data from them?
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
I just added some training sample. Would it work better if the input images in higher resolution?
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
Another question, Is the position of the camera is same for objects with same shape and different size?
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
yes, all object are observed in the same distance
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
@alirezazolanvari I just added the link to detection result using faster r-cnn
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
The text in images is clear? Can't you extract some data from them?
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
The text in images is clear? Can't you extract some data from them?
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
I just added some training sample. Would it work better if the input images in higher resolution?
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
I just added some training sample. Would it work better if the input images in higher resolution?
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
Another question, Is the position of the camera is same for objects with same shape and different size?
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
Another question, Is the position of the camera is same for objects with same shape and different size?
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
yes, all object are observed in the same distance
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
yes, all object are observed in the same distance
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
@alirezazolanvari I just added the link to detection result using faster r-cnn
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
@alirezazolanvari I just added the link to detection result using faster r-cnn
$endgroup$
– Hoang Dang Tuan
yesterday
|
show 2 more comments
1 Answer
1
active
oldest
votes
$begingroup$
If all objects are observed in the same distance and almost same angle, the relative height and width can be helpful features for recognizing objects with similar shape and different size. By this features different methods like GAN algorithms such as CoGAN and BiGAN may help you in this problem.
It should be noticed that for recognizing the size of the objects the features play more important role than the algorithms.
answered yesterday
alireza zolanvarialireza zolanvari
15311
$endgroup$
$begingroup$
I've always thought that GAN is used for generation. Do you have any link about applying GAN for object detection? I can't seem to find any.
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
What do you think if I used relative width and height as output for RPN instead of bounding box coordinates
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
When you can generate an entity well, obviously you can detect it accurately. In well-trained GAN networks, the discriminative network is powerful enough for recognizing generated entities. So, after you GAN had been trained, you can use the trained discriminative network for solving your problem.
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
If I understand correctly, you suggest that discriminator can be used to classify objects in my problem for better accuracy. What do you think I should do to improve my RPN accuracy?
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
I think giving the presented features (height and width) beside the images can improve the accuracy
$endgroup$
– alireza zolanvari
yesterday
|
show 4 more comments
Your Answer
StackExchange.ifUsing("editor", function ()
return StackExchange.using("mathjaxEditing", function ()
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix)
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
);
);
, "mathjax-editing");
StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "557"
;
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function()
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled)
StackExchange.using("snippets", function()
createEditor();
);
else
createEditor();
);
function createEditor()
StackExchange.prepareEditor(
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
bindNavPrevention: true,
postfix: "",
imageUploader:
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
,
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
);
);
Hoang Dang Tuan is a new contributor. Be nice, and check out our Code of Conduct.
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f47289%2fwhat-is-the-best-approach-to-detect-small-objects-with-similar-shape%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
$begingroup$
If all objects are observed in the same distance and almost same angle, the relative height and width can be helpful features for recognizing objects with similar shape and different size. By this features different methods like GAN algorithms such as CoGAN and BiGAN may help you in this problem.
It should be noticed that for recognizing the size of the objects the features play more important role than the algorithms.
answered yesterday
alireza zolanvarialireza zolanvari
15311
$endgroup$
$begingroup$
I've always thought that GAN is used for generation. Do you have any link about applying GAN for object detection? I can't seem to find any.
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
What do you think if I used relative width and height as output for RPN instead of bounding box coordinates
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
When you can generate an entity well, obviously you can detect it accurately. In well-trained GAN networks, the discriminative network is powerful enough for recognizing generated entities. So, after you GAN had been trained, you can use the trained discriminative network for solving your problem.
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
If I understand correctly, you suggest that discriminator can be used to classify objects in my problem for better accuracy. What do you think I should do to improve my RPN accuracy?
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
I think giving the presented features (height and width) beside the images can improve the accuracy
$endgroup$
– alireza zolanvari
yesterday
|
show 4 more comments
$begingroup$
If all objects are observed in the same distance and almost same angle, the relative height and width can be helpful features for recognizing objects with similar shape and different size. By this features different methods like GAN algorithms such as CoGAN and BiGAN may help you in this problem.
It should be noticed that for recognizing the size of the objects the features play more important role than the algorithms.
answered yesterday
alireza zolanvarialireza zolanvari
15311
$endgroup$
$begingroup$
I've always thought that GAN is used for generation. Do you have any link about applying GAN for object detection? I can't seem to find any.
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
What do you think if I used relative width and height as output for RPN instead of bounding box coordinates
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
When you can generate an entity well, obviously you can detect it accurately. In well-trained GAN networks, the discriminative network is powerful enough for recognizing generated entities. So, after you GAN had been trained, you can use the trained discriminative network for solving your problem.
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
If I understand correctly, you suggest that discriminator can be used to classify objects in my problem for better accuracy. What do you think I should do to improve my RPN accuracy?
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
I think giving the presented features (height and width) beside the images can improve the accuracy
$endgroup$
– alireza zolanvari
yesterday
|
show 4 more comments
$begingroup$
If all objects are observed in the same distance and almost same angle, the relative height and width can be helpful features for recognizing objects with similar shape and different size. By this features different methods like GAN algorithms such as CoGAN and BiGAN may help you in this problem.
It should be noticed that for recognizing the size of the objects the features play more important role than the algorithms.
answered yesterday
alireza zolanvarialireza zolanvari
15311
$endgroup$
If all objects are observed in the same distance and almost same angle, the relative height and width can be helpful features for recognizing objects with similar shape and different size. By this features different methods like GAN algorithms such as CoGAN and BiGAN may help you in this problem.
It should be noticed that for recognizing the size of the objects the features play more important role than the algorithms.
answered yesterday
alireza zolanvarialireza zolanvari
15311
answered yesterday
alireza zolanvarialireza zolanvari
15311
answered yesterday
alireza zolanvarialireza zolanvari
15311
answered yesterday
alireza zolanvarialireza zolanvari
15311
15311
$begingroup$
I've always thought that GAN is used for generation. Do you have any link about applying GAN for object detection? I can't seem to find any.
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
What do you think if I used relative width and height as output for RPN instead of bounding box coordinates
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
When you can generate an entity well, obviously you can detect it accurately. In well-trained GAN networks, the discriminative network is powerful enough for recognizing generated entities. So, after you GAN had been trained, you can use the trained discriminative network for solving your problem.
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
If I understand correctly, you suggest that discriminator can be used to classify objects in my problem for better accuracy. What do you think I should do to improve my RPN accuracy?
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
I think giving the presented features (height and width) beside the images can improve the accuracy
$endgroup$
– alireza zolanvari
yesterday
|
show 4 more comments
$begingroup$
I've always thought that GAN is used for generation. Do you have any link about applying GAN for object detection? I can't seem to find any.
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
What do you think if I used relative width and height as output for RPN instead of bounding box coordinates
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
When you can generate an entity well, obviously you can detect it accurately. In well-trained GAN networks, the discriminative network is powerful enough for recognizing generated entities. So, after you GAN had been trained, you can use the trained discriminative network for solving your problem.
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
If I understand correctly, you suggest that discriminator can be used to classify objects in my problem for better accuracy. What do you think I should do to improve my RPN accuracy?
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
I think giving the presented features (height and width) beside the images can improve the accuracy
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
I've always thought that GAN is used for generation. Do you have any link about applying GAN for object detection? I can't seem to find any.
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
I've always thought that GAN is used for generation. Do you have any link about applying GAN for object detection? I can't seem to find any.
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
What do you think if I used relative width and height as output for RPN instead of bounding box coordinates
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
What do you think if I used relative width and height as output for RPN instead of bounding box coordinates
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
When you can generate an entity well, obviously you can detect it accurately. In well-trained GAN networks, the discriminative network is powerful enough for recognizing generated entities. So, after you GAN had been trained, you can use the trained discriminative network for solving your problem.
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
When you can generate an entity well, obviously you can detect it accurately. In well-trained GAN networks, the discriminative network is powerful enough for recognizing generated entities. So, after you GAN had been trained, you can use the trained discriminative network for solving your problem.
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
If I understand correctly, you suggest that discriminator can be used to classify objects in my problem for better accuracy. What do you think I should do to improve my RPN accuracy?
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
If I understand correctly, you suggest that discriminator can be used to classify objects in my problem for better accuracy. What do you think I should do to improve my RPN accuracy?
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
I think giving the presented features (height and width) beside the images can improve the accuracy
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
I think giving the presented features (height and width) beside the images can improve the accuracy
$endgroup$
– alireza zolanvari
yesterday
|
show 4 more comments
Hoang Dang Tuan is a new contributor. Be nice, and check out our Code of Conduct.
Hoang Dang Tuan is a new contributor. Be nice, and check out our Code of Conduct.
Hoang Dang Tuan is a new contributor. Be nice, and check out our Code of Conduct.
Hoang Dang Tuan is a new contributor. Be nice, and check out our Code of Conduct.
Thanks for contributing an answer to Data Science Stack Exchange!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
Use MathJax to format equations. MathJax reference.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f47289%2fwhat-is-the-best-approach-to-detect-small-objects-with-similar-shape%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
$begingroup$
The text in images is clear? Can't you extract some data from them?
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
I just added some training sample. Would it work better if the input images in higher resolution?
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
Another question, Is the position of the camera is same for objects with same shape and different size?
$endgroup$
– alireza zolanvari
yesterday
$begingroup$
yes, all object are observed in the same distance
$endgroup$
– Hoang Dang Tuan
yesterday
$begingroup$
@alirezazolanvari I just added the link to detection result using faster r-cnn
$endgroup$
– Hoang Dang Tuan
yesterday