More on AI Image Processing


I have updated my stocks tracker project at \[https\://github.com/muzamono/stocks-tracker]\(https\://github.com/muzamono/stocks-tracker) to include live-time quote request using Moomoo API. 

The end goal? Autonomous trading or in the simplest term: trading bot.

Why? Since my portfolio is mainly consisted of US companies' security, the time difference is detrimental in keeping tabs of the moving markets. (And because I want to feel how to make money while sleeping ;) )

I have added etl-live/, signals/ and backtest/ into the repo for this update.

* etl-live: Contains the etl pipeline for the live tick through moomoo API. This is separate from the batch pipeline that pulls historical data from AlphaVantage API (Though moomoo API also provides historical data, maybe I will change this in the future)
* signals: Technical indicator library, shared by live pipeline and backtesting. The codes in this directory do the calculation for each of the indicator. Currently the signals consisted of 5 indicators: Simple Moving Average (SMA), Relative Strength Index (RSI), Bollinger Bands, Moving Average Convergence Divergence (MACD) and Volume (Relative Volume + Volume Trend)
* backtest: For testing the trading bot based on historical data. Contains scoring.py which normalizes the signals and combines into a weighted score as well as engine.py which simulates buy/hold/sell strategy based on the score and compares with buy-and-hold as a benchmark

The aim is to have the etl-live running live during trading days and update the price on an interval, which then get calculated by the “signals” codes and given a weighted score, which then fires “buy/hold/sell”, without any input from me.

I will need to decide the right interval of the price update since too many will make it a day trading (which is not my cup of tea) and too little make it not really worth to have a live quote request.

In the next post, I will talk about the testing of the algorithm and its finding.


A Step Into Autonomous Trading


In my “Receipt Tracker” project ([https://github.com/muzamono/receipt-tracker](https://github.com/muzamono/receipt-tracker)), one of the main aims is to implement image processing of payment receipts to directly input the expenses data into the app. 

Testing Claude.ai image processing through the chat interface returned promising result, but I'm not ready to jump the gun by subscribing to any LLM yet. Searching for inexpensive method to test this method, I came to 2 options: Leveraging LLM's (Gemini or DeepSeek) for the whole extraction, or the combination of free OCR tool (e.g., Tesseract, or a cloud OCR API) to convert the receipt image to raw text, then send that text to DeepSeek with JSON-extraction prompt. 

I will talk about the first option for this post.

Gemini gives free tier access to API, but trying to extract image data using hardcoded model number (gemini-2.0-flash or gemini-2.5-flash) proved fruitless with 429 RESOURCE\_EXHAUSTED error. However, further interrogation with Gemini helped me to gain a helpful intel; model = ‘gemini-flash-latest’, which will automatically route the request to whichever active Flash model has free-tier quota allocated for the key type.

```python
response = client.models.generate_content(
        model="gemini-flash-latest",
        contents=[processed_img, prompt],
        config=types.GenerateContentConfig(
            response_mime_type="application/json",
            response_schema=ReceiptData,  # Enforces structured output schema
            temperature=0.1,              # Strict accuracy for financial data
        ),
    )
```

Now that returned the result below with impressive accuracy compared to the sample image used. (Image at the top of the post.)

```python
{
  "merchant": "SUSHI YA",
  "date": "2026-02-14",
  "total_amount": 54.65,
  "currency": "MYR",
  "category": "Food",
  "line_items": [
    {
      "name": "GREEN TEA HOT",
      "quantity": 2.0,
      "unit_price": 2.5,
      "total": 5.0
    },
    {
      "name": "CHICKEN KATSU DON",
      "quantity": 1.0,
      "unit_price": 15.9,
      "total": 15.9
    },
    {
      "name": "CHICKEN KARAAGE RAMEN (TORI PAITA",
      "quantity": 1.0,
      "unit_price": 22.9,
      "total": 22.9
    },
    {
      "name": "RED PLATE",
      "quantity": 1.0,
      "unit_price": 3.33,
      "total": 3.33
    }
  ],
  "extraction_confidence": "high"
}
```

Gemini is quite promising for this use case, though my sample number is really small and not robust for production level yet. 

Now, onto DeepSeek.

Quick test of sample image with DeepSeek chat function returned promising results, but it turned out that the API models cannot receive input in image format (yet). So currently it is out of my consideration. 

All in all, I can say that Gemini API is capable of extracting data from images even in free tier and is usable in testing environment. As for implementing which method of data extraction, I may need to run further tests.


It was around late fall in 2023-24. I was in a small group of visitors to a steel mill of a major steelmaker in Japan and we were ushered towards one of the facilities in the steel-making line. 

Here, the hot-rolled steel coils run through the conveyer belt were scanned with a camera for any surface defects. The factory representative explained that the defects were detected using special software developed in-house, using defect images as training data. At that time, generative AI was already starting to be a popular topic worldwide, but Japan being quite “conservative” in software, there wasn't any mention of AI (人工知能 artificial intelligence in Japanese) by that representative. (At least that what I have remembered) 

“That's a neat way for defect inspection” I thought to myself, remembering that back at our factory it's done with the ol' blood-fueled retina. I wished that we someday could also build a system like that so that daily quality control tests would be more efficient. 

A lot has changed in AI throughout these years that I think someone with strong motivation and skills could attempt to develop something similar from inside their bedroom. Though image recognition is not a new technology, with the advent of AI it seems like this technology will be perfected in new future, if it isn't already. 

There is a lot of debate about whether this is a good thing or not (with con's usually regarding the use of facial recognition in surveillance), but for me, the future would introduce many more technology that was sci-fi to me 20 years ago, just like how space age was alien to person born at the start of the 20th century.

Hey, I'm Zakuan

About Me

Featured Projects

Stocks Tracker ETL

Receipt Tracker

Latest Blog Posts

A Step Into Autonomous Trading

More on AI Image Processing

AI in Image Recognition

Photo Gallery

More on AI Image Processing