Unity實現菜品識別的示例代碼

接口介紹:

識別超過9千種菜品,支持客戶創建屬於自己的菜品圖庫,可準確識別圖片中的菜品名稱、位置、卡路裡信息,並獲取百科信息,適用於多種客戶識別菜品的業務場景中。

創建應用:     

在產品服務中搜索圖像識別,創建應用,獲取AppID、APIKey、SecretKey信息:

查閱官方文檔,以下是菜品識別接口返回數據參數詳情:

定義數據結構:

using System;
 
/// <summary>
/// 菜品識別
/// </summary>
[Serializable]
public class DishRecognition 
{
    /// <summary>
    /// 唯一的log id,用於問題定位
    /// </summary>
    public float log_id;
    /// <summary>
    /// 返回結果數目,及result數組中的元素個數
    /// </summary>
    public int result_num;
    /// <summary>
    /// 菜品識別結果數組
    /// </summary>
    public DishRecognitionResult[] result;
}
 
/// <summary>
/// 菜品識別結果
/// </summary>
[Serializable]
public class DishRecognitionResult
{
    /// <summary>
    /// 菜名
    /// </summary>
    public string name;
    /// <summary>
    /// 卡路裡,每100g的卡路裡含量
    /// </summary>
    public float calorie;
    /// <summary>
    /// 識別結果中每一行的置信度值,0-1
    /// </summary>
    public float probability;
    /// <summary>
    /// 百科詞條
    /// </summary>
    public BaikeInfo baike_info;
}
 
[Serializable]
public class BaikeInfo
{
    /// <summary>
    /// 對應識別結果百度百科頁面鏈接
    /// </summary>
    public string baike_url;
    /// <summary>
    /// 對應識別結果百科圖片鏈接
    /// </summary>
    public string image_url;
    /// <summary>
    /// 對應識別結果百科內容描述
    /// </summary>
    public string description;
}

下載C# SDK:

下載完成後將AipSdk.dll動態庫導入到Unity中:

以下是調用接口時傳入的參數詳情:

封裝調用函數: 

using System;
using System.Collections.Generic;
using UnityEngine;
 
/// <summary>
/// 圖像識別
/// </summary>
public class ImageRecognition 
{
    //以下信息於百度開發者中心控制臺創建應用獲取
    private const string appID = "";
    private const string apiKey = "";
    private const string secretKey = "";
 
    /// <summary>
    /// 菜品識別
    /// </summary>
    /// <param name="bytes">圖片字節數據</param>
    /// <param name="topNum">返回預測得分top結果數,默認為5</param>
    /// <param name="filterThreshold">默認0.95,可以通過該參數調節識別效果,降低非菜識別率.</param>
    /// <param name="baikeNum">    返回百科信息的結果數,默認不返回</param>
    /// <returns></returns>
    public static DishRecognition Dish(byte[] bytes, int topNum = 5, float filterThreshold = 0.95f, int baikeNum = 0)
    {
        var client = new Baidu.Aip.ImageClassify.ImageClassify(apiKey, secretKey);
        try
        {
            var options = new Dictionary<string, object>
            {
                { "top_num", topNum },
                { "filter_threshold", Mathf.Clamp01(filterThreshold)},
                { "baike_num", baikeNum}
            };
            var response = client.DishDetect(bytes, options);
            DishRecognition dishRecognition = JsonConvert.DeserializeObject<DishRecognition>(response.ToString());
            return dishRecognition;
        }
        catch (Exception error)
        {
            Debug.LogError(error);
        }
        return null;
    }
}

測試圖片:

using System.IO;
using UnityEngine;
 
public class Example : MonoBehaviour
{
    private void Start()
    {
        ImageRecognition.Dish(File.ReadAllBytes(Application.dataPath + "/Picture.jpg"));
    }
}

到此這篇關於Unity實現菜品識別的示例代碼的文章就介紹到這瞭,更多相關Unity菜品識別內容請搜索WalkonNet以前的文章或繼續瀏覽下面的相關文章希望大傢以後多多支持WalkonNet!

推薦閱讀: