product overview updated

app.py

@@ -177,76 +177,67 @@ elif app_mode=="Project Details":
     # Project Overview
     st.write("## Project Overview:")
     st.write(""" 
-    1. **OCR to Extract Details** (20%):
-        - Use OCR to read brand details, pack size, brand name, etc.
-        - Train the model to read details from various products, including FMCG, OTC items, health supplements, personal care, and household items.
+        ### Problem Statement
+    _Develop a system that automates Amazon product listings from social media content, extracting and organizing details from posts to generate accurate, engaging, and optimized listings._
     
-    2. **Using OCR for Expiry Date Details** (10%):
-        - Validate expiry dates using OCR to read expiry and MRP details printed on items.
+    ---
     
-    3. **Image Recognition for Brand Recognition and Counting** (30%):
-        - Use machine learning to recognize brands and count product quantities from images.
+    ### Solution Overview
+    Our system simplifies the listing process by analyzing social media content, using OCR, image recognition, LLMs, and internet data to create professional Amazon listings.
     
-    4. **Detecting Freshness of Fresh Produce** (40%):
-        - Assess the freshness of fruits and vegetables by analyzing various visual cues and patterns.
-    """)
+    ---
     
-    st.write(""" 
-    Our project aims to leverage OCR and image recognition to enhance product packaging analysis and freshness detection. 
-    """)
-
-    # Proposal Round
-    st.write("## Proposal Round:")
-    st.write(""" 
-    **Format:** Use Case Submission & Code Review
-    - Selected teams will submit detailed use case scenarios they plan to solve.
-    - The submission should include a proposal outlining their approach and the code developed so far.
-    - The GRID team will provide a set of images for testing the model.
-    - Since this is an elimination stage, participants are encouraged to submit a video simulation of their solution on the image set provided to them, ensuring they can clearly articulate what they have solved. 
-    - Teams working on detecting the freshness of produce may choose any fresh fruit/vegetable/bread, etc., and submit the freshness index based on the model.
-    - The video will help demonstrate the effectiveness of their approach and provide a visual representation of their solution.
+    ### Task Breakdown
     
-    Teams with the most comprehensive and innovative proposals will proceed to the final stage.
-    """)
-
-    # Problem Statement
-    st.write("## Problem Statement:")
-    st.write(""" 
-    In today’s fast-paced retail environment, ensuring product quality and freshness is crucial for customer satisfaction. The Amazon Sambhav Challenge aims to address this issue by leveraging technology to enhance product packaging analysis and freshness detection. 
-
-    Traditional methods of checking freshness often involve manual inspection, which can be time-consuming and prone to human error. Furthermore, with the increasing variety of products available, a more automated and reliable solution is needed to streamline this process.
+    #### Task 1: OCR for Image and Label Details
+    **Objective:** Extract core product details from images, labels, and packaging found in social media posts.  
+    - **Tools:** PaddleOCR, LLMs.  
+    - **Approach:**  
+      - Use PaddleOCR to scan images for text, identifying product names, brands, and key features.  
+      - Apply LLMs to refine extracted data, categorize key information (product name, type, features), and enhance product descriptions.  
+      - Integrate internet sources to cross-verify product details, retrieve additional information, and collect metadata like the brand background or product specs.  
+    
+    ---
+    
+    #### Additional Task: Image Recognition & Object Counting
+    **Objective:** Quantify objects within social media images for batch products or multi-item listings.  
+    - **Tools:** YOLOv8.  
+    - **Approach:**  
+      - Train YOLOv8 on a relevant dataset to recognize specific product types or packaging layouts.  
+      - Use object detection counts to provide quantitative data (e.g., "3-item bundle"), enhancing accuracy in listings.  
+    
+    ---
+    
+    #### Task 2: Data Validation & Structuring
+    **Objective:** Organize and validate extracted information, ensuring it’s formatted to meet Amazon’s listing requirements.  
+    - **Tools:** Regex, LLMs.  
+    - **Approach:**  
+      - Format and validate extracted details into Amazon-compliant structures (titles, descriptions, bullet points).  
+      - Use regex and parser tools for accuracy checks.  
+      - Leverage LLMs to create compelling descriptions and marketing brochures.  
+      - Search online for supplementary media (images/videos) to enrich the listing.  
+    
+    ---
+    
+    #### Task 3: Amazon API Integration
+    **Objective:** Connect with Amazon’s API to publish fully formed product listings directly.  
+    - **Tools:** Amazon MWS or Selling Partner API.  
+    - **Approach:**  
+      - Send structured listing data (text, media, product details) to Amazon’s API endpoints.  
+      - Handle feedback for submission errors and make necessary adjustments.  
+      - Develop a UI/dashboard for users to preview and edit listings before publishing.  
+    
+    ---
+    
+    ### Future Enhancements
+    - **Model Improvement:** Further refine OCR and parsing accuracy.  
+    - **Dashboard Development:** Enable users to preview and customize listings.  
+    - **Multi-Market Compatibility:** Expand support to other e-commerce platforms.  
+    
+    This approach automates listing creation directly from social media content, helping sellers quickly launch optimized Amazon product pages.
 
-    Our project focuses on developing an advanced system that utilizes Optical Character Recognition (OCR) and image recognition techniques to automate the extraction of product details from packaging. This will not only improve accuracy but also increase efficiency in assessing product freshness.
     """)
-
-    # Proposed Solution
-    st.write("## Proposed Solution:")
-    st.write(""" 
-    Our solution is designed to tackle the problem by implementing the following key components:
-
-    ### 1. OCR for Product Detail Extraction
-    We will use OCR technology to accurately extract critical information from product packaging, including:
-    - Brand name
-    - Pack size
-    - Expiry date
-    - MRP details
-
-    This will allow for real-time analysis of product information, ensuring that customers receive accurate data about their purchases.
-
-    ### 2. Freshness Detection using Image Recognition
-    In conjunction with OCR, our model will utilize image recognition to assess the freshness of fruits, vegetables, and other perishable items. The model will be trained to classify products based on their appearance, detecting signs of spoilage and degradation. 
-
-    ### 3. Data Validation and Reporting
-    Our system will not only extract data but also validate expiry dates against the current date to ensure product safety. The results will be compiled into a user-friendly report that can be easily interpreted by retail staff.
-
-    ### 4. Video Simulation
-    To effectively demonstrate our solution, we will create a video simulation showcasing the functionality of our system. This will include real-time examples of how our model processes images and extracts relevant information.
-
-    ### 5. Proposal Submission
-    As part of the proposal round, we will provide a comprehensive submission outlining our approach, methodology, and the code developed thus far. This submission will highlight the effectiveness of our solution and our readiness to proceed to the final stage of the challenge.
     
-    Our team is committed to delivering a robust solution that not only meets but exceeds the expectations of the Amazon Sambhav Challenge.
-    """)
 
 elif app_mode == "Team Details":
     st.write("## Meet Our Team:")