hudvin
Re:Ask HN: Who wants to be hired? (June 2026)
on Monday June 01, 2026 @06:07PM (#48363297)
Location: Vienna
Remote: yes
Willing to relocate: no
Technologies: Python Stack/AWS/PDF Processing/OCR/FastAPI/data extraction/GPT integration
Résumé/CV: https://vadym.bartko.me/my_cv/
Email: [email protected]
Re:Ask HN: What Are You Working On? (February 2026)
on Monday February 09, 2026 @05:48PM (#46952688)
I study German and decided to write app to simplify some tasks:
1) generate anki cards from text
2) extract highlighted words from paper and generate anki cards
3) collection of texts/dialogs on random topics
4) and so on... )
not sure if someone needs it, but very helpful for me )
Re:Ask HN: Who wants to be hired? (August 2023)
on Tuesday August 01, 2023 @06:35PM (#36964187)
Location: Ukraine, Kyiv (safe mostly)
Remote: yes
Willing to relocate: want, but can't (
Technologies: Python backend stack, some computer vision, PDF processing (split, merge, ocr, text extraction, fixing all weird issues, mupdf, ghostscript - worked on pdf related projects), AWS
Resume:https://vadym.bartko.me/my_cv/
email: [email protected]
Re:Show HN: `pdf2searchablepdf` command-line tool to make PDF have sea...
on Thursday August 18, 2022 @01:48PM (#32512741)
Doesn't work very well.
First of all there are several separate problems: 1) detect if OCR is required 2) image optimization 3) preprocessing of broken pdf files. And all of them are not easy:
1) page could contain selectable text, but text can't be copied because embedded font doesn't contain glyph->symbol code mapping. Mapping table could contain complete garbage. Sometimes page could contain long urls (added by email services) but all text is provided as image. Sometimes text contains normal text and garbage. And many many other cases.
2) some old scanners generate pdf documents built from 2-5 pixel image stripes. Some of them try to do OCR (poorly). Some of them uses huge DPI. Sometimes you get uncompressed doc in which each page could take up to 200mb. So you need to convert pdf page to image. But you have to choose format and compression options. PNG is ok, but you have to choose correct options (for ghostscript). But output image will be huge. JPG is better, but quality could be low. Sometimes multistage optimization is required. Also tools like ghostscript, fitz or imagemagic doesn't handle all possible pdf/image.
3)weird pdfs - endless story. Poor fonts, broken fonts, very specific cases in pdf standard, issues with image extraction, table of content, viruses, embedded files, annotations, margins/paddings/rotations/translations.
Probably I have to write long post about this )
Re:Show HN: Pony – a messenger for mindful correspondence
on Friday November 19, 2021 @11:51AM (#29279240)
I was thinking about similar service for emails/news/forums/social networks. Main idea the same - slow updates.
Re:Lost nuclear device atop of Nanda Devi
on Saturday December 26, 2020 @08:20PM (#25547955)
Some info: I found this story while reading Fallen Giants (Maurice Isserman) - history of mountaineering in himalayas.
Lost nuclear device atop of Nanda Devi
Mathematical Coincidence
Re:Ask HN: Who wants to be hired? (June 2020)
on Monday June 01, 2020 @05:11PM (#23383870)
Location: Ukraine, Kyiv
Remote: Yes
Willing to relocate: someday
Technologies: Deep Learning/Python Backend stack - keras, pytorch, Flask, Docker, Kubernetes and so on. Fields - image processing, face detection, face recognition, object detection/classification, segmentation.
Résumé/CV: https://drive.google.com/file/d/1RF-eoiC5GMVhJwSvKZsy32bVto5...
Email: [email protected]
Last 12 month was working on AI-related startup (image search.)
Interested in remote position in Deep Learning/Computer Vision field.
Ask HN: Let's Build Something Together
Looks like many people got fired.Maybe someone wants to start small pet project or sort of startup (I know it's not the best time :D, but still...). I propose two things:1) if you already work on something or have idea - write some short info and who are you looking for2) if you want to join - describe your skills
Re:Ask HN: What are you learning?
on Sunday April 05, 2020 @05:40PM (#22788972)
Deutsch
some ancient history
NLP / Deep Learning
Re:Ask HN: Who wants to be hired? (April 2020)
on Wednesday April 01, 2020 @04:36PM (#22753251)
Location: Ukraine
Remote: Yes!!!
Willing to relocate: someday
Technologies: Deep Learning/Computer Vision (convnets, facenet, image classification, segmentation, opencv, keras, scikit-image etc), Python Backend Stack
CV: https://drive.google.com/open?id=1RF-eoiC5GMVhJwSvKZsy32bVto....
email: [email protected]
Re:Why Is Facebook Not in the Cloud Business?
on Monday March 23, 2020 @04:59PM (#22668683)
Yes, why not to sell data from dbs, backups, drives? :D
Re:Ask HN: Who wants to be hired right now?
on Monday March 23, 2020 @03:10PM (#22667563)
Location: Ukraine
Remote: Yes!!!
Willing to relocate: someday
Technologies: Deep Learning/Computer Vision (convnets, facenet, image classification, segmentation, opencv, keras, scikit-image etc), Python Backend Stack
CV: https://drive.google.com/open?id=1RF-eoiC5GMVhJwSvKZsy32bVto...
email: [email protected]
Re:Ask HN: What projects are you working on now?
on Saturday March 21, 2020 @06:54PM (#22650953)
I am working on search tool for images.
It detects faces, objects, tags, extracts metadata and provides search interface and API. So you can for example find image with "cat and dog near river with some person" I want to build enterprise level image search :)
Google Images, for example, uses in most cases alt text and surrounding content. Google Photos is limited to personal collections.
I have finished prototype and now trying to convert it to startup
Demo https://app.khumbu.im/search/5dff72e66483e25b40e0222e info https://khumbu.im
Changes in Google Advanced Protection – No Apps Without Google Play
https://support.google.com/accounts/answer/9764949?p=ap-and&visit_id=637201535597737202-11306229&rd=1To help protect against malware, new app installations from most sources outside the Play Store are blocked on any Android device that has a Google Account enrolled in Advanced Protection.You’ll still be able to install Android apps from:Google Play App stores that were pre-installed by...
Re:Show HN: Khumbu – image search engine as service
on Thursday January 30, 2020 @02:40PM (#22194650)
comments from founder:
Current status - MVP
I have been working on this project during last 12 month and now want to show it to community and ask for some feedback.
Demo search: https://app.khumbu.im/search/5dff72e66483e25b40e0222e
So what is this?
1. Khumbu is an image search engine based on computer vision and deep learning.
2. Workflow: upload your images via API or web app and run search queries via API/app.
3. Right now it provides object detection, classification, exif extraction, face detection, nsfw scoring.
4. Tech details: images are processed using celery workers, after that all information is moved to ElasticSearch to serve user queries. Most part is deployed in k8s cluster, but some processing is done on remote machines with GPUs.
Soon we want to add: 1. face recognition (public and user specific faces)
2. similarity search (based on embeddings)
3. search images of specific place
4. better query processing (synonyms/related terms etc).
NOTE: Sorry, but right now indexing is disabled due to high cost of GPUs.
Show HN: Khumbu – image search engine as service
Re:Google backtracks on search results design
on Saturday January 25, 2020 @07:06AM (#22145935)
Small self-promotions: We are working on image search engine - https://khumbu.im, demo (MVP stage)https://app.khumbu.im/search/5dff72e66483e25b40e0222e . We use DL to understand content of images and provide better search results. Soon we are going to add face recognition, improve object detection and semantic analysis.
Re:Ask HN: Who's Looking for a Co-Founder?
on Wednesday October 23, 2019 @05:41PM (#21339328)
I am working on image search engine based on AI (demo: http://demo.khumbu.im/ ). Khumbu detected faces, objects, scenes, metadata on images etc and provides flexible search using this information (see http://demo.khumbu.im/examples/). UI is a little bit ugly(sorry, I am backend person), but everything else is up and running. Currently I work on REST api, k8s deployment and some AI-related things.
I also got some small investments to rent servers.
I am looking for person who could work on UI related things, product improvement and has experience in startups. Europe is preferable.
my email: [email protected]
Re:Ask HN: Who is seeking a cofounder?
on Monday June 24, 2019 @03:06PM (#20267223)
I am working on image search engine (something like elasticsearch but for images). I apply some deep learning magic (like object detection, classification etc), face recognition, exif extraction and some other. MVP is almost ready and soon I will be able to handle quries like:
content="dog and cat on the table" exif.apperture>5 exif.data>2005 faces.count >4
But I am pretty weak at frontend development and pitching/presentations. email: [email protected]