Update README.md

README.md

@@ -6,39 +6,44 @@ tags:
 - fintech
 - ocr-pre-processing
 - pytorch
+- banking
 license: mit
 ---
 
 # 💳 Th-Slip-OCR-K: Precision Financial Detection
 
 ![Static Badge](https://img.shields.io/badge/Architecture-YOLOv8_Nano-blue?style=flat-square)
-![Static Badge](https://img.shields.io/badge/Precision-99.5%25-green?style=flat-square)
+![Static Badge](https://img.shields.io/badge/Classes-6_Zones-orange?style=flat-square)
+![Static Badge](https://img.shields.io/badge/Precision-99.8%25-green?style=flat-square)
 ![Static Badge](https://img.shields.io/badge/Device-Apple_M4_Silicon-grey?style=flat-square)
 
-**A lightweight, high-velocity object detection model engineered to extract key telemetry from Kasikorn Bank (K-Bank) transaction slips.**
+**A lightweight, high-velocity object detection model engineered to extract full telemetry from Kasikorn Bank (K-Bank) transaction slips.**
 
 ---
 
 ## ⚡ Overview
 **Th-Slip-OCR-K** is a specialized computer vision model designed as a pre-processing engine for OCR pipelines. It isolates specific regions of interest within financial documents, eliminating noise and enabling higher accuracy for text extraction systems.
 
+**🚀 V2 Update:** Enhanced detection capabilities to cover sender/receiver names and masked account numbers.
+
 * **Architecture:** Ultralytics YOLOv8 Nano (v8.3.0)
 * **Training Hardware:** Apple M4 Silicon (Metal Performance Shaders)
 * **Optimization:** Low-latency inference, suitable for edge devices and mobile deployment.
 
-## 🎯 Detection Classes
-The model is trained to identify three critical zones with high confidence:
+## 🎯 Detection Classes (Updated)
+The model is now trained to identify **6 critical zones** with high confidence:
 
-| Class ID | Label | Description |
+| Label | Description | Context |
 | :--- | :--- | :--- |
-| `0` | **`amout`** | The numeric transaction value (net amount). |
-| `1` | **`date`** | The timestamp of the transaction. |
-| `2` | **`transaction`** | The type of operation (e.g., Transfer Success). |
-
-*> **Note:** Class `amout` preserves the original dataset labeling configuration.*
+| **`amount`** | Numeric transaction value | Net transfer amount (e.g., 100.00) |
+| **`accnum`** | Account Number | Supports masked formats (e.g., `xxx-2-x8574-x`) |
+| **`date`** | Timestamp | Date and Time of transaction |
+| **`pp1`** | Sender Name | Name of the person initiating the transfer |
+| **`pp2`** | Receiver Name | Name of the beneficiary |
+| **`transaction`** | Transaction Type | Operation status (e.g., Transfer Success) |
 
 ## 💻 Usage (Python)
-Seamlessly integrate into your workflow using the `ultralytics` library without manual downloads.
+Seamlessly integrate into your workflow using the `ultralytics` library.
 
 ```python
 from ultralytics import YOLO
@@ -54,15 +59,16 @@ results[0].show()
 ```
 
 ## 📊 Performance Metrics
-Evaluated on a specific K-Bank validation set:
+Evaluated on the latest K-Bank validation set (103 samples):
 
 * **mAP50:** 0.995 (99.5%)
-* **Precision:** 0.997
-* **Recall:** 1.0
+* **Precision:** 0.998 (High fidelity)
+* **Recall:** 1.0 (Zero miss rate)
 
 ## ⚠️ Scope & Limitations
 * **Domain Specific:** Optimized exclusively for Kasikorn Bank (Green Theme) slip layouts.
-* **Lighting Conditions:** Performs best on well-lit, digital receipts or clear screenshots.
+* **Privacy Aware:** The model detects masked account numbers (x) accurately but cannot reveal hidden digits without external database verification.
 * **Educational Purpose:** Developed as a Proof-of-Concept for automated household accounting.
 
-Maintained by Pondet
+---
+Maintained by **Pondet**