Image Identification with Very Limited Samples

Imekamilika Ilichapishwa Miaka 5 iliyopita Kulipwa wakati wa kujifungua
Imekamilika Kulipwa wakati wa kujifungua

Skills you must have:

Solid experience in Image Identification, CNN, Machine Learning, Algorithm toning, Python

NOTE:

this project is NOT for beginners.

------

Requirements:

1) training data:

- total products: 1000+

- each product has 1 or 2 images (image quality, size, resolution, angle, light condition varies)

2) functions:

- Identification is based on structure of the product not color.

- Convert all color images into grey image (if this would simplify the work for you)

- design and develop code to create a data model and extract features based on training data

- with testing data, achieve 85% or above accuracy of identification

3) output:

- code in python with sufficient comments (if private modules/libs are used, shall also be included)

- data models trained or features extracted

- necessary documents

4) Performance

- with trained models and features extracted, each identification shall take no more than 1 sec

- identification accuracy > 85%

- able to handle most image problem including (light conditions, angles, size difference)

More requirements:
1) The training part need to be scalable since we keep adding new products/images to the system
2) Identification part, as part of service online, shall take less than 10 sec to finish
3) All processing can be executed on regular CPU env (GPU not required)
4) Language: Python 2.7 on Linux,

Deliverables:
- if there's any binary data created by system, please include format explanation in document
- process of re-train system with new data in document
- parameter toning in document

Training data: https://s3.amazonaws.com/product-image-id-sample-data/backview_samples.gz

NOTE:
* the training model has to be scalable to re-train when new products are added to the system.
You deliver 2 system: training system, and identification system

The image quality may have all kinds of issues. So please download the images and assess the work before you propose.

sorry, above link has problem. here is the good one I've verified:
https://s3.amazonaws.com/product-image-id-sample-data/backview_samples.tar.gz

----- Below are agreements between me and Zhou H. -----
Major milestones:
1) 08/10 --
a) binary of training system would be delivered with output format definition/explanation.
b) basic usage instruction shall be delivered
c) employer will follow the instruction and use the binary to verify results
d) bugs shall be fixed before 08/12 to secure the quality of training system.

2) 08/17 --
a) binary of Identification system would be delivered with output format definition/explanation.
identification result shall have accuracy of 99% with top 5 results ( for 100 images tested, 99 shall have the correct match detected within top 5 results)
where top 1 result has the accuracy of 85% or above
b) usage instruction of both the training system (if any change) and identification shall be delivered
c) employer will do following type of tests:
- adding new products, or/and new images to existing products to the system and verify that image of the product can be identified
- use different images of the same products in training set to validate results
d) bugs shall be fixed by 08/22. there might be multiple rounds of releasing of binary and feed back of testing results

3) 08/22 ($800 release)
a) when all testing of binary have passed and meet requirements, source code would be released to employer
b) employer would release $800 upon receiving of complete source code
c) employer would review code and repeat above testing with the source code
d) bugs are expected to be fixed by 08/24 to secure the completion of the whole project

4) 08/27 ($200 release)
a) 2nd release of source code with sufficient comments, design documents, test cases, major algorithms listed

[MODIFICATION] above milestone item 2), for top 5 results, the expected coverage is "90%".

Best Effort and Damage Control:
- the employer fully trust that the bidder is a professional who would do his best to finish this project
- both sides will cooperate to demonstrate high professionalism and secure the success of this project
- Should anything happen that this project can not be finished, the employer is willing to cover the $300 fee charged by Freelancer for this project.

-----------------------------
Requirements:
1) the system will contain 2 sub-systems: training system and identification system
2) both systems will be developed using Python 2.7 and open source modules. Any in house developed modules imported shall be included as deliverables.
3) both systems will be executed at regular linux box such as Mac osx ( regular CPU, no GPU)
4) the training system shall be able to train 10000+ products within 10 minutes. adding new products or new images to existing product shall only require re-train the data model, no coding shall be required.
5) identification system shall be able to identify an image among 10,000 products within 30 sec to 1 minute
6) Image for training and identification shall ignore color difference.
7) Both systems shall have high tolerance of
- image on different background (white, grey, black, partial colored etc)
- product rotated to different angle than the training picture (upside down, horizontal vs vertical, etc)
- image is taken at 45 degree of the product, not right top of the product
- handle as grey image, color difference (red. blue, green) shall be ignored
- certain level of image distortion

Algorithm Image Processing Machine Learning (ML) Neural Networks Python

Kitambulisho cha Mradi: #17467156

Kuhusu mradi

27 mapendekezo Mradi wa mbali Ipo mtandaoni %project.latestActivity_relativeTime|badilisha%

Imetuzwa kwa:

AImobile

Hello I'm an IP and OCR expert. I have developed many OCR and Pattern Recognition app such as ALPR, Face Recognition, 1/2D Barcode, Captcha and so on. You can see some demos at my portfolio. if you are interested pl Zaidi

$1029 USD kwa siku 10
(Maoni 4)
5.1

27 wafanyakazi huru wanazabuni wastani wa $1347 kwa kazi hii

Yknox

Hi, I am Ren, Software Engineer in China. I've just read your job posting and I am very interested. I'm a certificated freelancer with over 1000 good reviews from clients. I have experienced knowledge in every pa Zaidi

$10000 USD kwa siku 70
(Maoni 63)
7.3
mingxiao2008

Hello, Dear. How are you? I have read your project description. I am going to implement your project using python sklearn. I am very interested in your project and am ready for discussing with you about project. Zaidi

$1029 USD kwa siku 10
(Maoni 52)
7.0
AItechnology

Experienced data scientist who has extensively worked on computer vision projects including object detection, text area detection, OCR, pedestrian tracking using CNN/ open CV/ dlib. Would like to see sample images for Zaidi

$1000 USD kwa siku 10
(Maoni 64)
6.8
AzzkaNoor

I am confident that I can implement this project as I have read all the details. There are some questions to ask to the clarify some doubts, so please message me. Eager to present my portfolio over the chat. Please Zaidi

$1029 USD kwa siku 10
(Maoni 14)
6.7
uzairrzahid

Hi. My name is Uzair.I am in final semester of my masters in Electrical Engineering. I am doing my thesis in biomedical signal processing and Machine learning. I have more than 3 years of experience in MATLAB/PYTHON Zaidi

$972 USD kwa siku 10
(Maoni 73)
6.1
nkoutroumpinis

Hey there! i am working as a professional data scientist with lots of experience on machine learning in general. You can check out my profile reviews to get a first impression of the work i am delivering. We can disc Zaidi

$972 USD kwa siku 10
(Maoni 21)
6.1
moeed10

Hi, I can develop both systems. I have a lot of experience in Image Identification, CNN, Machine Learning, Algorithm toning, Computer Vision applications / image and video processing in mobile and windows applicati Zaidi

$1000 USD kwa siku 10
(Maoni 8)
6.0
invincible1428

Hello, Greetings of the day.!! Your project attracted my attention at first glance, because I've really rich experience in Machine Learning & Python Programming. I have worked on several similar projects before! I'm Zaidi

$1333 USD kwa siku 10
(Maoni 60)
5.8
suju8811

Dear client! I read your project carefully so I am interested in your project. I am a opencv & tensorflow & c++ & python expert and developer. And also I am a deep learning expert. I know what you really want. its Zaidi

$1000 USD kwa siku 10
(Maoni 9)
5.5
iitmshanker

Hello, I have been very active doing machine learning projects and many of them have been done on tensorflow framework. Classifying fruits based on their texture, news classifier, cancer tumor grade classification, Zaidi

$1500 USD kwa siku 10
(Maoni 22)
5.1
Angel521

Hello I'm very interesting your project. I have experiences in this kind of project. I am able to implement your requirements with high quality. Please discuss more details over chat. Thanks.

$1000 USD kwa siku 10
(Maoni 10)
4.6
jjmutumi

Hello, I'm a software developer with more than 8 years experience using Python. I'm new to the platform so don't have any reviews but I've previous experience with machine learning and data set training to solve pro Zaidi

$750 USD kwa siku 10
(Maoni 8)
4.7
murtaza1122

Hi Please share details of data , how many labels are there ? I am afraid that classifying around 500 categories from 1000 images is impossible using Deep Learning. I have been working on Machine Learning Reg Zaidi

$1000 USD kwa siku 30
(Maoni 1)
4.1
dilichan

Hi, I am an engineer with years of experience working on machine learning and computer vision projects. My expertise is on vision based projects using deep learning. I have done many projects such as face recogniti Zaidi

$750 USD kwa siku 10
(Maoni 7)
3.9
lnarayanan90

Hey, I am keen in getting involved with this project. I am adept in working with CNN, DNN and RNN, and also familiar in working with standard frameworks such as Yolo, CNN-RNN COCO etc. Transfer learning from Alexnet Zaidi

$1000 USD kwa siku 25
(Maoni 10)
3.8
BilalMusani

I have worked on CNNS for emotion classification in 3D spaces as well as DCGANs for creating 3d models from 2D images. Samples can be sent on request.

$777 USD kwa siku 20
(Maoni 2)
2.4
ArStudioz

Hi Mapyang. I see your proposal and understand that you are looking for an Image Identification. I have expertise in Image Identification, CNN, Machine Learning, Algorithm toning, Python etc. I have developed Zaidi

$1350 USD kwa siku 10
(Maoni 2)
2.0
teamspirit3

Hi, dear, I have 7+ years of experiences in Data Sciences , Machine Learning in Image processing. And I like Jave and Python to implement my Algorithm. I can show my machine learning works via teamviewer, if you want Zaidi

$1111 USD kwa siku 10
(Maoni 3)
1.6
magadhmindslx

Dear Sir, I have gone through project description and interested in taking it up. Posted bid amount is indicative and a more accurate I can give once more details are shared. Looking forward to hearing from you. Thanks

$972 USD kwa siku 10
(Maoni 2)
0.8
jayaramkapil

I have research experience in convolutional neural nets and their implementation using tensorflow and Python. If you are interested you can contact me. Relevant Skills and Experience Machine learning, Deep learning

$972 USD kwa siku 10
(Maoni 0)
0.0